Search Results for author: Alejandro Ribeiro

Found 171 papers, 28 papers with code

Loss Shaping Constraints for Long-Term Time Series Forecasting

no code implementations14 Feb 2024 Ignacio Hounie, Javier Porras-Valenzuela, Alejandro Ribeiro

We propose a practical Primal-Dual algorithm to tackle it, and demonstrate that the proposed approach exhibits competitive average performance in time series forecasting benchmarks, while shaping the distribution of errors across the predicted window.

Time Series Time Series Forecasting

Towards a Foundation Model for Brain Age Prediction using coVariance Neural Networks

no code implementations12 Feb 2024 Saurabh Sihag, Gonzalo Mateos, Alejandro Ribeiro

Brain age is the estimate of biological age derived from neuroimaging datasets using machine learning algorithms.

Sampling and Uniqueness Sets in Graphon Signal Processing

no code implementations11 Jan 2024 Alejandro Parada-Mayorga, Alejandro Ribeiro

We state the formal definition of a $\Lambda-$removable set and conditions under which a bandlimited graphon signal can be represented in a unique way when its samples are obtained from the complement of a given $\Lambda-$removable set in the graphon.

LPAC: Learnable Perception-Action-Communication Loops with Applications to Coverage Control

1 code implementation10 Jan 2024 Saurav Agarwal, Ramya Muthukrishnan, Walker Gosrich, Vijay Kumar, Alejandro Ribeiro

Coverage control is the problem of navigating a robot swarm to collaboratively monitor features or a phenomenon of interest not known a priori.

Imitation Learning

Reply to 'Comments on Graphon Signal Processing' [arXiv:2310.14683]

no code implementations5 Jan 2024 Luana Ruiz, Luiz F. O. Chamon, Alejandro Ribeiro

This technical note addresses an issue [arXiv:2310. 14683] with the proof (but not the statement) of [arXiv:2003. 05030, Proposition 4].

LEMMA valid

Resilient Constrained Reinforcement Learning

no code implementations28 Dec 2023 Dongsheng Ding, Zhengyan Huan, Alejandro Ribeiro

It is challenging to identify appropriate constraint specifications due to the undefined trade-off between the reward maximization objective and the constraint satisfaction, which is ubiquitous in constrained decision-making.

Decision Making reinforcement-learning +1

Robust Stochastically-Descending Unrolled Networks

2 code implementations25 Dec 2023 Samar Hadou, Navid Naderializadeh, Alejandro Ribeiro

To tackle these problems, we provide deep unrolled architectures with a stochastic descent nature by imposing descending constraints during training.

Image Inpainting

Neural Tangent Kernels Motivate Graph Neural Networks with Cross-Covariance Graphs

no code implementations16 Oct 2023 Shervin Khalafi, Saurabh Sihag, Alejandro Ribeiro

Building upon this concept, we investigate NTKs and alignment in the context of graph neural networks (GNNs), where our analysis reveals that optimizing alignment translates to optimizing the graph representation or the graph shift operator in a GNN.

Time Series Time Series Prediction

Non Commutative Convolutional Signal Models in Neural Networks: Stability to Small Deformations

no code implementations5 Oct 2023 Alejandro Parada-Mayorga, Landon Butler, Alejandro Ribeiro

In this paper we discuss the results recently published in~[1] about algebraic signal models (ASMs) based on non commutative algebras and their use in convolutional neural networks.

Network Alignment with Transferable Graph Autoencoders

1 code implementation5 Oct 2023 Jiashu He, Charilaos I. Kanatsoulis, Alejandro Ribeiro

Network alignment is the task of establishing one-to-one correspondences between the nodes of different graphs and finds a plethora of applications in high-impact domains.

Data Augmentation Transfer Learning

Learning State-Augmented Policies for Information Routing in Communication Networks

1 code implementation30 Sep 2023 Sourajit Das, Navid Naderializadeh, Alejandro Ribeiro

This paper examines the problem of information routing in a large-scale communication network, which can be formulated as a constrained statistical learning problem having access to only local information.

Asynchronous Perception-Action-Communication with Graph Neural Networks

no code implementations18 Sep 2023 Saurav Agarwal, Alejandro Ribeiro, Vijay Kumar

A fundamental challenge in decentralized PAC systems is to decide what information to communicate with the neighboring robots and how to take actions while utilizing the information shared by the neighbors.

Computational Efficiency

Transferability of Convolutional Neural Networks in Stationary Learning Tasks

1 code implementation21 Jul 2023 Damian Owerko, Charilaos I. Kanatsoulis, Jennifer Bondarchuk, Donald J. Bucci Jr, Alejandro Ribeiro

To accomplish this we investigate the properties of CNNs for tasks where the underlying signals are stationary.

Intrinsically motivated graph exploration using network theories of human curiosity

1 code implementation11 Jul 2023 Shubhankar P. Patankar, Mathieu Ouellet, Juan Cervino, Alejandro Ribeiro, Kieran A. Murphy, Dani S. Bassett

The theories view curiosity as an intrinsic motivation to optimize for topological features of subgraphs induced by nodes visited in the environment.

Recommendation Systems reinforcement-learning

Last-Iterate Convergent Policy Gradient Primal-Dual Methods for Constrained MDPs

no code implementations NeurIPS 2023 Dongsheng Ding, Chen-Yu Wei, Kaiqing Zhang, Alejandro Ribeiro

To fill this gap, we employ the Lagrangian method to cast a constrained MDP into a constrained saddle-point problem in which max/min players correspond to primal/dual variables, respectively, and develop two single-time-scale policy-based primal-dual algorithms with non-asymptotic convergence of their policy iterates to an optimal constrained policy.

Solving Large-scale Spatial Problems with Convolutional Neural Networks

no code implementations14 Jun 2023 Damian Owerko, Charilaos I. Kanatsoulis, Alejandro Ribeiro

Over the past decade, deep learning research has been accelerated by increasingly powerful hardware, which facilitated rapid growth in the model complexity and the amount of data ingested.

Transfer Learning

Resilient Constrained Learning

no code implementations NeurIPS 2023 Ignacio Hounie, Alejandro Ribeiro, Luiz F. O. Chamon

This paper presents a constrained learning approach that adapts the requirements while simultaneously solving the learning task.

Fairness Federated Learning +1

Geometric Graph Filters and Neural Networks: Limit Properties and Discriminability Trade-offs

no code implementations29 May 2023 Zhiyang Wang, Luana Ruiz, Alejandro Ribeiro

This paper studies the relationship between a graph neural network (GNN) and a manifold neural network (MNN) when the graph is constructed from a set of points sampled from the manifold, thus encoding geometric information.

Point Cloud Classification

Explainable Brain Age Prediction using coVariance Neural Networks

1 code implementation NeurIPS 2023 Saurabh Sihag, Gonzalo Mateos, Corey McMillan, Alejandro Ribeiro

In computational neuroscience, there has been an increased interest in developing machine learning algorithms that leverage brain imaging data to provide estimates of "brain age" for an individual.

Stochastic Unrolled Federated Learning

1 code implementation24 May 2023 Samar Hadou, Navid Naderializadeh, Alejandro Ribeiro

We introduce Stochastic UnRolled Federated learning (SURF), a method that expands algorithm unrolling to federated learning in order to expedite its convergence.

Federated Learning Rolling Shutter Correction

Lie Group Algebra Convolutional Filters

no code implementations8 May 2023 Harshat Kumar, Alejandro Parada-Mayorga, Alejandro Ribeiro

We show that traditional group convolutions are one particular instantiation of a more general Lie group algebra homomorphism associated to an algebraic signal model rooted in the Lie group algebra $L^{1}(G)$ for given Lie group $G$.

Transferability of coVariance Neural Networks and Application to Interpretable Brain Age Prediction using Anatomical Features

1 code implementation2 May 2023 Saurabh Sihag, Gonzalo Mateos, Corey T. McMillan, Alejandro Ribeiro

To gauge the advantages offered by VNNs in neuroimaging data analysis, we focus on the task of "brain age" prediction using cortical thickness features.

Tangent Bundle Convolutional Learning: from Manifolds to Cellular Sheaves and Back

no code implementations20 Mar 2023 Claudio Battiloro, Zhiyang Wang, Hans Riess, Paolo Di Lorenzo, Alejandro Ribeiro

We define tangent bundle filters and tangent bundle neural networks (TNNs) based on this convolution operation, which are novel continuous architectures operating on tangent bundle signals, i. e. vector fields over the manifolds.

Graph Neural Networks for Decentralized Multi-Agent Perimeter Defense

no code implementations23 Jan 2023 Elijah S. Lee, Lifeng Zhou, Alejandro Ribeiro, Vijay Kumar

In this work, we study the problem of decentralized multi-agent perimeter defense that asks for computing actions for defenders with local perceptions and communications to maximize the capture of intruders.

Imitation Learning

Graphon Pooling for Reducing Dimensionality of Signals and Convolutional Operators on Graphs

no code implementations15 Dec 2022 Alejandro Parada-Mayorga, Zhiyang Wang, Alejandro Ribeiro

In this paper we propose a pooling approach for convolutional information processing on graphs relying on the theory of graphons and limits of dense graph sequences.

Dimensionality Reduction

Convolutional Filtering on Sampled Manifolds

no code implementations20 Nov 2022 Zhiyang Wang, Luana Ruiz, Alejandro Ribeiro

The increasing availability of geometric data has motivated the need for information processing over non-Euclidean domains modeled as manifolds.

Stable and Transferable Hyper-Graph Neural Networks

no code implementations11 Nov 2022 Mikhail Hayhoe, Hans Riess, Victor M. Preciado, Alejandro Ribeiro

To do so, we provide a framework for bounding the stability and transferability error of GNNs across arbitrary graphs via spectral similarity.

Algebraic Convolutional Filters on Lie Group Algebras

no code implementations31 Oct 2022 Harshat Kumar, Alejandro Parada-Mayorga, Alejandro Ribeiro

Group convolutional neural networks are a useful tool for utilizing symmetries known to be in a signal; however, they require that the signal is defined on the group itself.

Learning with Multigraph Convolutional Filters

no code implementations28 Oct 2022 Landon Butler, Alejandro Parada-Mayorga, Alejandro Ribeiro

In this paper, we introduce a convolutional architecture to perform learning when information is supported on multigraphs.

Predicting Brain Age using Transferable coVariance Neural Networks

no code implementations28 Oct 2022 Saurabh Sihag, Gonzalo Mateos, Corey McMillan, Alejandro Ribeiro

We have recently studied covariance neural networks (VNNs) that operate on sample covariance matrices using the architecture derived from graph convolutional networks, and we showed VNNs enjoy significant advantages over traditional data analysis approaches.

Space-Time Graph Neural Networks with Stochastic Graph Perturbations

no code implementations28 Oct 2022 Samar Hadou, Charilaos Kanatsoulis, Alejandro Ribeiro

Space-time graph neural networks (ST-GNNs) are recently developed architectures that learn efficient graph representations of time-varying data.

Transfer Learning

A State-Augmented Approach for Learning Optimal Resource Management Decisions in Wireless Networks

no code implementations28 Oct 2022 Yiğit Berkay Uslu, Navid Naderializadeh, Mark Eisen, Alejandro Ribeiro

We propose a state-augmented parameterization for the RRM policy, where alongside the instantaneous network states, the RRM policy takes as input the set of dual variables corresponding to the constraints.

Management

Neural Networks with Quantization Constraints

1 code implementation27 Oct 2022 Ignacio Hounie, Juan Elenter, Alejandro Ribeiro

Furthermore, we show that dual variables indicate the sensitivity of the objective with respect to constraint perturbations.

Image Classification Quantization

Multi-Target Tracking with Transferable Convolutional Neural Networks

1 code implementation27 Oct 2022 Damian Owerko, Charilaos I. Kanatsoulis, Jennifer Bondarchuk, Donald J. Bucci Jr, Alejandro Ribeiro

Multi-target tracking (MTT) is a classical signal processing task, where the goal is to estimate the states of an unknown number of moving targets from noisy sensor measurements.

Transfer Learning

Training Graph Neural Networks on Growing Stochastic Graphs

no code implementations27 Oct 2022 Juan Cervino, Luana Ruiz, Alejandro Ribeiro

In this paper, we propose to learn GNNs on very large graphs by leveraging the limit object of a sequence of growing graphs, the graphon.

Multi-task Bias-Variance Trade-off Through Functional Constraints

no code implementations27 Oct 2022 Juan Cervino, Juan Andres Bazerque, Miguel Calvo-Fullana, Alejandro Ribeiro

In this paper we draw intuition from the two extreme learning scenarios -- a single function for all tasks, and a task-specific function that ignores the other tasks dependencies -- to propose a bias-variance trade-off.

domain classification Multi-Task Learning

Tangent Bundle Filters and Neural Networks: from Manifolds to Cellular Sheaves and Back

no code implementations26 Oct 2022 Claudio Battiloro, Zhiyang Wang, Hans Riess, Paolo Di Lorenzo, Alejandro Ribeiro

In this work we introduce a convolution operation over the tangent bundle of Riemannian manifolds exploiting the Connection Laplacian operator.

Denoising

Unsupervised Optimal Power Flow Using Graph Neural Networks

no code implementations17 Oct 2022 Damian Owerko, Fernando Gama, Alejandro Ribeiro

Optimal power flow (OPF) is a critical optimization problem that allocates power to the generators in order to satisfy the demand at a minimum cost.

Convolutional Neural Networks on Manifolds: From Graphs and Back

no code implementations1 Oct 2022 Zhiyang Wang, Luana Ruiz, Alejandro Ribeiro

Deep neural network architectures have been proved as a powerful technique to solve problems based on these data residing on the manifold.

Federated Representation Learning via Maximal Coding Rate Reduction

no code implementations1 Oct 2022 Juan Cervino, Navid Naderializadeh, Alejandro Ribeiro

We propose a federated methodology to learn low-dimensional representations from a dataset that is distributed among several clients.

Federated Learning Representation Learning

Learning Globally Smooth Functions on Manifolds

no code implementations1 Oct 2022 Juan Cervino, Luiz F. O. Chamon, Benjamin D. Haeffele, Rene Vidal, Alejandro Ribeiro

To do so, it shows that under typical conditions the problem of learning a Lipschitz continuous function on a manifold is equivalent to a dynamically weighted manifold regularization problem.

Automatic Data Augmentation via Invariance-Constrained Learning

1 code implementation29 Sep 2022 Ignacio Hounie, Luiz F. O. Chamon, Alejandro Ribeiro

Despite its ubiquity, its effectiveness depends on the choices of which transformations to apply, when to do so, and how often.

 Ranked #1 on Image Classification on SVHN (Percentage correct metric)

Data Augmentation Image Classification

Learning Decentralized Strategies for a Perimeter Defense Game with Graph Neural Networks

no code implementations24 Sep 2022 Elijah S. Lee, Lifeng Zhou, Alejandro Ribeiro, Vijay Kumar

We consider the problem of finding decentralized strategies for multi-agent perimeter defense games.

Convolutional Learning on Multigraphs

no code implementations23 Sep 2022 Landon Butler, Alejandro Parada-Mayorga, Alejandro Ribeiro

In this paper, we develop convolutional information processing on multigraphs and introduce convolutional multigraph neural networks (MGNNs).

Stability of Aggregation Graph Neural Networks

no code implementations8 Jul 2022 Alejandro Parada-Mayorga, Zhiyang Wang, Fernando Gama, Alejandro Ribeiro

We also conclude that in Agg-GNNs the selectivity of the mapping operators is tied to the properties of the filters only in the first layer of the CNN stage.

State-Augmented Learnable Algorithms for Resource Management in Wireless Networks

1 code implementation5 Jul 2022 Navid Naderializadeh, Mark Eisen, Alejandro Ribeiro

We consider resource management problems in multi-user wireless networks, which can be cast as optimizing a network-wide utility function, subject to constraints on the long-term average performance of users across the network.

Management

Self-Consistency of the Fokker-Planck Equation

1 code implementation2 Jun 2022 Zebang Shen, Zhenfu Wang, Satyen Kale, Alejandro Ribeiro, Amin Karbasi, Hamed Hassani

In this paper, we exploit this concept to design a potential function of the hypothesis velocity fields, and prove that, if such a function diminishes to zero during the training procedure, the trajectory of the densities generated by the hypothesis velocity fields converges to the solution of the FPE in the Wasserstein-2 sense.

coVariance Neural Networks

1 code implementation31 May 2022 Saurabh Sihag, Gonzalo Mateos, Corey McMillan, Alejandro Ribeiro

Moreover, our experiments on multi-resolution datasets also demonstrate that VNNs are amenable to transferability of performance over covariance matrices of different dimensions; a feature that is infeasible for PCA-based approaches.

Learning Graph Structure from Convolutional Mixtures

no code implementations19 May 2022 Max Wasserman, Saurabh Sihag, Gonzalo Mateos, Alejandro Ribeiro

Machine learning frameworks such as graph neural networks typically rely on a given, fixed graph to exploit relational inductive biases and thus effectively learn from network data.

Graph Learning Link Prediction

Representation Power of Graph Neural Networks: Improved Expressivity via Algebraic Analysis

no code implementations19 May 2022 Charilaos I. Kanatsoulis, Alejandro Ribeiro

Despite the remarkable success of Graph Neural Networks (GNNs), the common belief is that their representation power is limited and that they are at most as expressive as the Weisfeiler-Lehman (WL) algorithm.

Graph Classification

Learning Resilient Radio Resource Management Policies with Graph Neural Networks

1 code implementation7 Mar 2022 Navid Naderializadeh, Mark Eisen, Alejandro Ribeiro

We consider the problems of user selection and power control in wireless interference networks, comprising multiple access points (APs) communicating with a group of user equipment devices (UEs) over a shared wireless medium.

Fairness Management

A Lagrangian Duality Approach to Active Learning

no code implementations8 Feb 2022 Juan Elenter, Navid Naderializadeh, Alejandro Ribeiro

We consider the pool-based active learning problem, where only a subset of the training data is labeled, and the goal is to query a batch of unlabeled samples to be labeled so as to maximally improve model performance.

Active Learning Informativeness

Large-Scale Graph Reinforcement Learning in Wireless Control Systems

no code implementations24 Jan 2022 Vinicius Lima, Mark Eisen, Konstantinos Gatsis, Alejandro Ribeiro

As the number of learnable parameters in a neural network grows with the size of the input signal, deep reinforcement learning may fail to scale, limiting the immediate generalization of such scheduling and resource allocation policies to large-scale systems.

reinforcement-learning Reinforcement Learning (RL) +1

Learning Connectivity-Maximizing Network Configurations

no code implementations14 Dec 2021 Daniel Mox, Vijay Kumar, Alejandro Ribeiro

In this letter we propose a data-driven approach to optimizing the algebraic connectivity of a team of robots.

Unity

Transferability Properties of Graph Neural Networks

no code implementations9 Dec 2021 Luana Ruiz, Luiz F. O. Chamon, Alejandro Ribeiro

In this paper, we study the problem of training GNNs on graphs of moderate size and transferring them to large-scale graphs.

Movie Recommendation

Adversarial Robustness with Semi-Infinite Constrained Learning

no code implementations NeurIPS 2021 Alexander Robey, Luiz F. O. Chamon, George J. Pappas, Hamed Hassani, Alejandro Ribeiro

In particular, we leverage semi-infinite optimization and non-convex duality theory to show that adversarial training is equivalent to a statistical problem over perturbation distributions, which we characterize completely.

Adversarial Robustness

Stability of Neural Networks on Manifolds to Relative Perturbations

no code implementations10 Oct 2021 Zhiyang Wang, Luana Ruiz, Alejandro Ribeiro

Hence, in this paper, we analyze the stability properties of convolutional neural networks on manifolds to understand the stability of GNNs on large graphs.

Training Stable Graph Neural Networks Through Constrained Learning

no code implementations7 Oct 2021 Juan Cervino, Luana Ruiz, Alejandro Ribeiro

Graph Neural Networks (GNN) rely on graph convolutions to learn features from network data.

Space-Time Graph Neural Networks

no code implementations ICLR 2022 Samar Hadou, Charilaos I. Kanatsoulis, Alejandro Ribeiro

We introduce a generic definition of convolution operators that mimic the diffusion process of signals over its underlying support.

An Agnostic Approach to Federated Learning with Class Imbalance

no code implementations ICLR 2022 Zebang Shen, Juan Cervino, Hamed Hassani, Alejandro Ribeiro

Federated Learning (FL) has emerged as the tool of choice for training deep models over heterogeneous and decentralized datasets.

Federated Learning

Convolutional Filtering and Neural Networks with Non Commutative Algebras

no code implementations23 Aug 2021 Alejandro Parada-Mayorga, Landon Butler, Alejandro Ribeiro

In this paper we introduce and study the algebraic generalization of non commutative convolutional neural networks.

Wide and Deep Graph Neural Network with Distributed Online Learning

no code implementations19 Jul 2021 Zhan Gao, Fernando Gama, Alejandro Ribeiro

At training time, the joint wide and deep architecture learns nonlinear representations from data.

Movie Recommendation

Learning Decentralized Wireless Resource Allocations with Graph Neural Networks

no code implementations3 Jul 2021 Zhiyang Wang, Mark Eisen, Alejandro Ribeiro

We consider the broad class of decentralized optimal resource allocation problems in wireless networks, which can be formulated as a constrained statistical learning problems with a localized information structure.

Scalable Perception-Action-Communication Loops with Convolutional and Graph Neural Networks

1 code implementation24 Jun 2021 Ting-Kuei Hu, Fernando Gama, Tianlong Chen, Wenqing Zheng, Zhangyang Wang, Alejandro Ribeiro, Brian M. Sadler

Our framework is implemented by a cascade of a convolutional and a graph neural network (CNN / GNN), addressing agent-level visual perception and feature learning, as well as swarm-level communication, local information aggregation and agent action inference, respectively.

Imitation Learning

Stability of Graph Convolutional Neural Networks to Stochastic Perturbations

no code implementations19 Jun 2021 Zhan Gao, Elvin Isufi, Alejandro Ribeiro

In particular, it proves the expected output difference between the GCNN over random perturbed graphs and the GCNN over the nominal graph is upper bounded by a factor that is linear in the link loss probability.

Learning by Transference: Training Graph Neural Networks on Growing Graphs

no code implementations7 Jun 2021 Juan Cervino, Luana Ruiz, Alejandro Ribeiro

Graph neural networks (GNNs) use graph convolutions to exploit network invariances and learn meaningful feature representations from network data.

Stability to Deformations of Manifold Filters and Manifold Neural Networks

no code implementations7 Jun 2021 Zhiyang Wang, Luana Ruiz, Alejandro Ribeiro

The most important practical consequence of this analysis is to shed light on the behavior of graph filters and GNNs in large-scale graphs.

Training Robust Graph Neural Networks with Topology Adaptive Edge Dropping

no code implementations5 Jun 2021 Zhan Gao, Subhrajit Bhattacharya, Leiming Zhang, Rick S. Blum, Alejandro Ribeiro, Brian M. Sadler

Graph neural networks (GNNs) are processing architectures that exploit graph structural information to model representations from network data.

Data Augmentation

Graph Neural Networks for Decentralized Multi-Robot Submodular Action Selection

1 code implementation18 May 2021 Lifeng Zhou, Vishnu D. Sharma, QingBiao Li, Amanda Prorok, Alejandro Ribeiro, Pratap Tokekar, Vijay Kumar

We demonstrate the performance of our GNN-based learning approach in a scenario of active target tracking with large networks of robots.

Decision Making Motion Planning

Composable Learning with Sparse Kernel Representations

no code implementations26 Mar 2021 Ekaterina Tolstaya, Ethan Stump, Alec Koppel, Alejandro Ribeiro

We present a reinforcement learning algorithm for learning sparse non-parametric controllers in a Reproducing Kernel Hilbert Space.

Learning Connectivity for Data Distribution in Robot Teams

1 code implementation8 Mar 2021 Ekaterina Tolstaya, Landon Butler, Daniel Mox, James Paulos, Vijay Kumar, Alejandro Ribeiro

To overcome this challenge, we propose a task-agnostic, decentralized, low-latency method for data distribution in ad-hoc networks using Graph Neural Networks (GNN).

Constrained Learning with Non-Convex Losses

no code implementations8 Mar 2021 Luiz F. O. Chamon, Santiago Paternain, Miguel Calvo-Fullana, Alejandro Ribeiro

In this paper, we overcome this issue by learning in the empirical dual domain, where constrained statistical learning problems become unconstrained and deterministic.

Adversarial Robustness Fairness +1

Stability of Neural Networks on Riemannian Manifolds

no code implementations3 Mar 2021 Zhiyang Wang, Luana Ruiz, Alejandro Ribeiro

We further construct a manifold neural network architecture with these filters.

State Augmented Constrained Reinforcement Learning: Overcoming the Limitations of Learning with Rewards

no code implementations23 Feb 2021 Miguel Calvo-Fullana, Santiago Paternain, Luiz F. O. Chamon, Alejandro Ribeiro

Thus, as we illustrate by an example, while previous methods can fail at finding optimal policies, running the dual dynamics while executing the augmented policy yields an algorithm that provably samples actions from the optimal policy.

reinforcement-learning Reinforcement Learning (RL)

Large Scale Distributed Collaborative Unlabeled Motion Planning with Graph Policy Gradients

no code implementations11 Feb 2021 Arbaaz Khan, Vijay Kumar, Alejandro Ribeiro

We are able to demonstrate the scalability of our methods for a large number of robots by employing a graph neural network (GNN) to parameterize policies for the robots.

Motion Planning

Sufficiently Accurate Model Learning for Planning

no code implementations11 Feb 2021 Clark Zhang, Santiago Paternain, Alejandro Ribeiro

This paper introduces the constrained Sufficiently Accurate model learning approach, provides examples of such problems, and presents a theorem on how close some approximate solutions can be.

Synthesizing Decentralized Controllers with Graph Neural Networks and Imitation Learning

no code implementations29 Dec 2020 Fernando Gama, QingBiao Li, Ekaterina Tolstaya, Amanda Prorok, Alejandro Ribeiro

Dynamical systems consisting of a set of autonomous agents face the challenge of having to accomplish a global task, relying only on local information.

Imitation Learning

Trust but Verify: Assigning Prediction Credibility by Counterfactual Constrained Learning

no code implementations24 Nov 2020 Luiz F. O. Chamon, Santiago Paternain, Alejandro Ribeiro

Prediction credibility measures, in the form of confidence intervals or probability distributions, are fundamental in statistics and machine learning to characterize model robustness, detect out-of-distribution samples (outliers), and protect against adversarial attacks.

counterfactual

Sinkhorn Natural Gradient for Generative Models

no code implementations NeurIPS 2020 Zebang Shen, Zhenfu Wang, Alejandro Ribeiro, Hamed Hassani

In this regard, we propose a novel Sinkhorn Natural Gradient (SiNG) algorithm which acts as a steepest descent method on the probability space endowed with the Sinkhorn divergence.

Unsupervised Learning for Asynchronous Resource Allocation in Ad-hoc Wireless Networks

no code implementations5 Nov 2020 Zhiyang Wang, Mark Eisen, Alejandro Ribeiro

We capture the asynchrony by modeling the activation pattern as a characteristic of each node and train a policy-based resource allocation method.

Nonlinear State-Space Generalizations of Graph Convolutional Neural Networks

no code implementations27 Oct 2020 Luana Ruiz, Fernando Gama, Alejandro Ribeiro, Elvin Isufi

In this work, we approach GCNNs from a state-space perspective revealing that the graph convolutional module is a minimalistic linear state-space model, in which the state update matrix is the graph shift operator.

Multi-task Supervised Learning via Cross-learning

no code implementations24 Oct 2020 Juan Cervino, Juan Andres Bazerque, Miguel Calvo-Fullana, Alejandro Ribeiro

In this paper we consider a problem known as multi-task learning, consisting of fitting a set of classifier or regression functions intended for solving different tasks.

Image Classification Multi-Task Learning

Graph and graphon neural network stability

no code implementations23 Oct 2020 Luana Ruiz, Zhiyang Wang, Alejandro Ribeiro

We then extend this analysis by interpreting the graphon neural network as a generating model for GNNs on deterministic and stochastic graphs instantiated from the original and perturbed graphons.

Movie Recommendation

Stability of Algebraic Neural Networks to Small Perturbations

no code implementations22 Oct 2020 Alejandro Parada-Mayorga, Alejandro Ribeiro

Algebraic neural networks (AlgNNs) are composed of a cascade of layers each one associated to and algebraic signal model, and information is mapped between layers by means of a nonlinearity function.

Quiver Signal Processing (QSP)

no code implementations22 Oct 2020 Alejandro Parada-Mayorga, Hans Riess, Alejandro Ribeiro, Robert Ghrist

In this paper we state the basics for a signal processing framework on quiver representations.

Discriminability of Single-Layer Graph Neural Networks

no code implementations17 Oct 2020 Samuel Pfrommer, Fernando Gama, Alejandro Ribeiro

We define a notion of discriminability tied to the stability of the architecture, show that GNNs are at least as discriminative as linear graph filter banks, and characterize the signals that cannot be discriminated by either.

Policy Gradient for Continuing Tasks in Non-stationary Markov Decision Processes

no code implementations16 Oct 2020 Santiago Paternain, Juan Andres Bazerque, Alejandro Ribeiro

To that end we compute unbiased stochastic gradients of the value function which we use as ascent directions to update the policy.

Navigate

Spherical Convolutional Neural Networks: Stability to Perturbations in SO(3)

no code implementations12 Oct 2020 Zhan Gao, Fernando Gama, Alejandro Ribeiro

Spherical convolutional neural networks (Spherical CNNs) learn nonlinear representations from 3D data by exploiting the data structure and have shown promising performance in shape analysis, object classification, and planning among others.

Object Recognition

Graph-Adaptive Activation Functions for Graph Neural Networks

1 code implementation14 Sep 2020 Bianca Iancu, Luana Ruiz, Alejandro Ribeiro, Elvin Isufi

Activation functions are crucial in graph neural networks (GNNs) as they allow defining a nonlinear family of functions to capture the relationship between the input graph data and their representations.

Recommendation Systems

Federated Classification using Parsimonious Functions in Reproducing Kernel Hilbert Spaces

no code implementations8 Sep 2020 Maria Peifer, Alejandro Ribeiro

Instead, each agent must form a local model and decide what information is fundamental to the learning problem, which will be sent to a central unit.

Signal Processing

Model-Free Design of Control Systems over Wireless Fading Channels

no code implementations3 Sep 2020 Vinicius Lima, Mark Eisen, Konstantinos Gatsis, Alejandro Ribeiro

Wireless control systems replace traditional wired communication with wireless networks to exchange information between actuators, plants and sensors in a control system.

Algebraic Neural Networks: Stability to Deformations

no code implementations3 Sep 2020 Alejandro Parada-Mayorga, Alejandro Ribeiro

An AlgNN is a stacked layered information processing structure where each layer is conformed by an algebra, a vector space and a homomorphism between the algebra and the space of endomorphisms of the vector space.

Graph Neural Networks: Architectures, Stability and Transferability

no code implementations4 Aug 2020 Luana Ruiz, Fernando Gama, Alejandro Ribeiro

They are presented here as generalizations of convolutional neural networks (CNNs) in which individual layers contain banks of graph convolutional filters instead of banks of classical convolutional filters.

Recommendation Systems

Resource Allocation via Model-Free Deep Learning in Free Space Optical Communications

no code implementations27 Jul 2020 Zhan Gao, Mark Eisen, Alejandro Ribeiro

This paper investigates the general problem of resource allocation for mitigating channel fading effects in Free Space Optical (FSO) communications.

Computational Efficiency Stochastic Optimization

Sinkhorn Barycenter via Functional Gradient Descent

no code implementations NeurIPS 2020 Zebang Shen, Zhenfu Wang, Alejandro Ribeiro, Hamed Hassani

In this paper, we consider the problem of computing the barycenter of a set of probability distributions under the Sinkhorn divergence.

Balancing Rates and Variance via Adaptive Batch-Size for Stochastic Optimization Problems

no code implementations2 Jul 2020 Zhan Gao, Alec Koppel, Alejandro Ribeiro

Stochastic gradient descent is a canonical tool for addressing stochastic optimization problems, and forms the bedrock of modern machine learning and statistics.

Stochastic Optimization

Resource Allocation via Graph Neural Networks in Free Space Optical Fronthaul Networks

no code implementations26 Jun 2020 Zhan Gao, Mark Eisen, Alejandro Ribeiro

This paper investigates the optimal resource allocation in free space optical (FSO) fronthaul networks.

Zeroth-order Deterministic Policy Gradient

no code implementations12 Jun 2020 Harshat Kumar, Dionysios S. Kalogerias, George J. Pappas, Alejandro Ribeiro

Deterministic Policy Gradient (DPG) removes a level of randomness from standard randomized-action Policy Gradient (PG), and demonstrates substantial empirical success for tackling complex dynamic problems involving Markov decision processes.

Graph Neural Networks for Motion Planning

no code implementations11 Jun 2020 Arbaaz Khan, Alejandro Ribeiro, Vijay Kumar, Anthony G. Francis

This paper investigates the feasibility of using Graph Neural Networks (GNNs) for classical motion planning problems.

Motion Planning

Wide and Deep Graph Neural Networks with Distributed Online Learning

no code implementations11 Jun 2020 Zhan Gao, Fernando Gama, Alejandro Ribeiro

At testing time, the deep part (nonlinear) is left unchanged, while the wide part is retrained online, leading to a convex problem.

Probably Approximately Correct Constrained Learning

no code implementations NeurIPS 2020 Luiz. F. O. Chamon, Alejandro Ribeiro

To overcome this issue, we prove that under mild conditions the empirical dual problem of constrained learning is also a PAC constrained learner that now leads to a practical constrained learning algorithm based solely on solving unconstrained problems.

PAC learning Robust classification

Counterfactual Programming for Optimal Control

no code implementations L4DC 2020 Luiz F.O. Chamon, Santiago Paternain, Alejandro Ribeiro

In recent years, considerable work has been done to tackle the issue of designing control laws based on observations to allow unknown dynamical systems to perform pre-specified tasks.

counterfactual

Graphon Neural Networks and the Transferability of Graph Neural Networks

no code implementations NeurIPS 2020 Luana Ruiz, Luiz. F. O. Chamon, Alejandro Ribeiro

These graph convolutions combine information from adjacent nodes using coefficients that are shared across all nodes.

Stochastic Graph Neural Networks

no code implementations4 Jun 2020 Zhan Gao, Elvin Isufi, Alejandro Ribeiro

Graph neural networks (GNNs) model nonlinear representations in graph data with applications in distributed agent coordination, control, and planning among others.

Graph Neural Networks for Decentralized Controllers

no code implementations23 Mar 2020 Fernando Gama, Ekaterina Tolstaya, Alejandro Ribeiro

Dynamical systems comprised of autonomous agents arise in many relevant problems such as multi-agent robotics, smart grids, or smart cities.

Graphon Signal Processing

no code implementations10 Mar 2020 Luana Ruiz, Luiz F. O. Chamon, Alejandro Ribeiro

Graphons are infinite-dimensional objects that represent the limit of convergent sequences of graphs as their number of nodes goes to infinity.

Graphs, Convolutions, and Neural Networks: From Graph Filters to Graph Neural Networks

1 code implementation8 Mar 2020 Fernando Gama, Elvin Isufi, Geert Leus, Alejandro Ribeiro

We also introduce GNN extensions using edge-varying and autoregressive moving average graph filters and discuss their properties.

Recommendation Systems

Graphon Pooling in Graph Neural Networks

no code implementations3 Mar 2020 Alejandro Parada-Mayorga, Luana Ruiz, Alejandro Ribeiro

In this work, we propose a new strategy for pooling and sampling on GNNs using graphons which preserves the spectral properties of the graph.

Dimensionality Reduction

Wireless Power Control via Counterfactual Optimization of Graph Neural Networks

no code implementations17 Feb 2020 Navid Naderializadeh, Mark Eisen, Alejandro Ribeiro

We consider the problem of downlink power control in wireless networks, consisting of multiple transmitter-receiver pairs communicating with each other over a single shared wireless medium.

counterfactual

The empirical duality gap of constrained statistical learning

no code implementations12 Feb 2020 Luiz. F. O. Chamon, Santiago Paternain, Miguel Calvo-Fullana, Alejandro Ribeiro

This paper is concerned with the study of constrained statistical learning problems, the unconstrained version of which are at the core of virtually all of modern information processing.

VGAI: End-to-End Learning of Vision-Based Decentralized Controllers for Robot Swarms

no code implementations6 Feb 2020 Ting-Kuei Hu, Fernando Gama, Tianlong Chen, Zhangyang Wang, Alejandro Ribeiro, Brian M. Sadler

More specifically, we consider that each robot has access to a visual perception of the immediate surroundings, and communication capabilities to transmit and receive messages from other neighboring robots.

Gated Graph Recurrent Neural Networks

1 code implementation3 Feb 2020 Luana Ruiz, Fernando Gama, Alejandro Ribeiro

Graph processes exhibit a temporal structure determined by the sequence index and and a spatial structure determined by the graph support.

EdgeNets:Edge Varying Graph Neural Networks

1 code implementation21 Jan 2020 Elvin Isufi, Fernando Gama, Alejandro Ribeiro

This is a general linear and local operation that a node can perform and encompasses under one formulation all existing graph convolutional neural networks (GCNNs) as well as graph attention networks (GATs).

Graph Attention

Graph Neural Networks for Decentralized Multi-Robot Path Planning

1 code implementation12 Dec 2019 Qing-Biao Li, Fernando Gama, Alejandro Ribeiro, Amanda Prorok

We train the model to imitate an expert algorithm, and use the resulting model online in decentralized planning involving only local communication and local observations.

Decision Making

Risk-Aware MMSE Estimation

no code implementations6 Dec 2019 Dionysios S. Kalogerias, Luiz. F. O. Chamon, George J. Pappas, Alejandro Ribeiro

Despite the simplicity and intuitive interpretation of Minimum Mean Squared Error (MMSE) estimators, their effectiveness in certain scenarios is questionable.

Model-Free Learning of Optimal Ergodic Policies in Wireless Systems

no code implementations10 Nov 2019 Dionysios S. Kalogerias, Mark Eisen, George J. Pappas, Alejandro Ribeiro

Upon further assuming the use of near-universal policy parameterizations, we also develop explicit bounds on the gap between optimal values of initial, infinite dimensional resource allocation problems, and dual values of their parameterized smoothed surrogates.

Constrained Reinforcement Learning Has Zero Duality Gap

no code implementations NeurIPS 2019 Santiago Paternain, Luiz. F. O. Chamon, Miguel Calvo-Fullana, Alejandro Ribeiro

The later is generally addressed by formulating the conflicting requirements as a constrained RL problem and solved using Primal-Dual methods.

reinforcement-learning Reinforcement Learning (RL)

Stability of Graph Neural Networks to Relative Perturbations

no code implementations21 Oct 2019 Fernando Gama, Joan Bruna, Alejandro Ribeiro

In this paper, we are set to study the effect that a change in the underlying graph topology that supports the signal has on the output of a GNN.

Movie Recommendation Recommendation Systems

On the Sample Complexity of Actor-Critic Method for Reinforcement Learning with Function Approximation

no code implementations18 Oct 2019 Harshat Kumar, Alec Koppel, Alejandro Ribeiro

Actor-critic algorithms combine the merits of both approaches by alternating between steps to estimate the value function and policy gradient updates.

reinforcement-learning Reinforcement Learning (RL)

Optimal Wireless Resource Allocation with Random Edge Graph Neural Networks

no code implementations4 Sep 2019 Mark Eisen, Alejandro Ribeiro

We consider the problem of optimally allocating resources across a set of transmitters and receivers in a wireless network.

Optimal WDM Power Allocation via Deep Learning for Radio on Free Space Optics Systems

no code implementations21 Jun 2019 Zhan Gao, Mark Eisen, Alejandro Ribeiro

Radio on Free Space Optics (RoFSO), as a universal platform for heterogeneous wireless services, is able to transmit multiple radio frequency signals at high rates in free space optical networks.

Stability of Graph Scattering Transforms

1 code implementation NeurIPS 2019 Fernando Gama, Joan Bruna, Alejandro Ribeiro

In this work, we extend scattering transforms to network data by using multiresolution graph wavelets, whose computation can be obtained by means of graph convolutions.

Transfer Learning

Stability Properties of Graph Neural Networks

no code implementations11 May 2019 Fernando Gama, Joan Bruna, Alejandro Ribeiro

Graph neural networks (GNNs) have emerged as a powerful tool for nonlinear processing of graph signals, exhibiting success in recommender systems, power outage prediction, and motion planning, among others.

Motion Planning Recommendation Systems

Sparse multiresolution representations with adaptive kernels

no code implementations7 May 2019 Maria Peifer, Luiz. F. O. Chamon, Santiago Paternain, Alejandro Ribeiro

To address the complexity issues, we then write the function estimation problem as a sparse functional program that explicitly minimizes the support of the representation leading to low complexity solutions.

Invariance-Preserving Localized Activation Functions for Graph Neural Networks

no code implementations29 Mar 2019 Luana Ruiz, Fernando Gama, Antonio G. Marques, Alejandro Ribeiro

Graph neural networks (GNNs) are information processing architectures tailored to these graph signals and made of stacked layers that compose graph convolutional filters with nonlinear activation functions.

Recommendation Systems

Learning Decentralized Controllers for Robot Swarms with Graph Neural Networks

1 code implementation25 Mar 2019 Ekaterina Tolstaya, Fernando Gama, James Paulos, George Pappas, Vijay Kumar, Alejandro Ribeiro

We consider the problem of finding distributed controllers for large networks of mobile robots with interacting dynamics and sparsely available communications.

Robotics

Gated Graph Convolutional Recurrent Neural Networks

1 code implementation5 Mar 2019 Luana Ruiz, Fernando Gama, Alejandro Ribeiro

Graph processes model a number of important problems such as identifying the epicenter of an earthquake or predicting weather.

Node Classification

A Stochastic Trust Region Method for Non-convex Minimization

no code implementations ICLR 2020 Zebang Shen, Pan Zhou, Cong Fang, Alejandro Ribeiro

We target the problem of finding a local minimum in non-convex finite-sum minimization.

Generalizing Graph Convolutional Neural Networks with Edge-Variant Recursions on Graphs

no code implementations4 Mar 2019 Elvin Isufi, Fernando Gama, Alejandro Ribeiro

This paper reviews graph convolutional neural networks (GCNNs) through the lens of edge-variant graph filters.

General Classification

Sufficiently Accurate Model Learning

no code implementations19 Feb 2019 Clark Zhang, Arbaaz Khan, Santiago Paternain, Alejandro Ribeiro

In this paper, we investigate a method to regularize model learning techniques to provide better error characteristics for traditional control and planning algorithms.

Functional Nonlinear Sparse Models

no code implementations1 Nov 2018 Luiz. F. O. Chamon, Yonina C. Eldar, Alejandro Ribeiro

Even if they are, recovering sparse solutions using convex relaxations requires assumptions that may be hard to meet in practice.

Robust classification Spectrum Cartography +1

Median activation functions for graph neural networks

no code implementations29 Oct 2018 Luana Ruiz, Fernando Gama, Antonio G. Marques, Alejandro Ribeiro

Graph neural networks (GNNs) have been shown to replicate convolutional neural networks' (CNNs) superior performance in many problems involving graphs.

Efficient Distributed Hessian Free Algorithm for Large-scale Empirical Risk Minimization via Accumulating Sample Strategy

no code implementations26 Oct 2018 Majid Jahani, Xi He, Chenxin Ma, Aryan Mokhtari, Dheevatsa Mudigere, Alejandro Ribeiro, Martin Takáč

In this paper, we propose a Distributed Accumulated Newton Conjugate gradiEnt (DANCE) method in which sample size is gradually increasing to quickly obtain a solution whose empirical loss is under satisfactory statistical accuracy.

Learning Optimal Resource Allocations in Wireless Systems

no code implementations21 Jul 2018 Mark Eisen, Clark Zhang, Luiz. F. O. Chamon, Daniel D. Lee, Alejandro Ribeiro

This paper considers the design of optimal resource allocation policies in wireless communication systems which are generically modeled as a functional optimization problem with stochastic constraints.

Scalable Centralized Deep Multi-Agent Reinforcement Learning via Policy Gradients

no code implementations22 May 2018 Arbaaz Khan, Clark Zhang, Daniel D. Lee, Vijay Kumar, Alejandro Ribeiro

When the number of agents increases, the dimensionality of the input and control spaces increase as well, and these methods do not scale well.

Distributed Optimization Multi-agent Reinforcement Learning +2

Nonparametric Stochastic Compositional Gradient Descent for Q-Learning in Continuous Markov Decision Problems

1 code implementation19 Apr 2018 Alec Koppel, Ekaterina Tolstaya, Ethan Stump, Alejandro Ribeiro

We consider Markov Decision Problems defined over continuous state and action spaces, where an autonomous agent seeks to learn a map from its states to actions so as to maximize its long-term discounted accumulation of rewards.

Q-Learning Stochastic Optimization

MIMO Graph Filters for Convolutional Neural Networks

no code implementations6 Mar 2018 Fernando Gama, Antonio G. Marques, Alejandro Ribeiro, Geert Leus

Superior performance and ease of implementation have fostered the adoption of Convolutional Neural Networks (CNNs) for a wide array of inference and reconstruction tasks.

Convolutional Neural Networks Via Node-Varying Graph Filters

no code implementations27 Oct 2017 Fernando Gama, Geert Leus, Antonio G. Marques, Alejandro Ribeiro

Convolutional neural networks (CNNs) are being applied to an increasing number of problems and fields due to their superior performance in classification and regression tasks.

Decentralized Online Learning with Kernels

no code implementations11 Oct 2017 Alec Koppel, Santiago Paternain, Cedric Richard, Alejandro Ribeiro

That is, we establish that with constant step-size selections agents' functions converge to a neighborhood of the globally optimal one while satisfying the consensus constraints as the penalty parameter is increased.

General Classification Multi-class Classification +2

First-Order Adaptive Sample Size Methods to Reduce Complexity of Empirical Risk Minimization

no code implementations NeurIPS 2017 Aryan Mokhtari, Alejandro Ribeiro

Theoretical analyses show that the use of adaptive sample size methods reduces the overall computational cost of achieving the statistical accuracy of the whole dataset for a broad range of deterministic and stochastic first-order methods.

Large Scale Empirical Risk Minimization via Truncated Adaptive Newton Method

no code implementations22 May 2017 Mark Eisen, Aryan Mokhtari, Alejandro Ribeiro

In this paper, we propose a novel adaptive sample size second-order method, which reduces the cost of computing the Hessian by solving a sequence of ERM problems corresponding to a subset of samples and lowers the cost of computing the Hessian inverse using a truncated eigenvalue decomposition.

Second-order methods

Greedy Sampling of Graph Signals

no code implementations5 Apr 2017 Luiz. F. O. Chamon, Alejandro Ribeiro

In contrast to traditional signal processing, the irregularity of the signal domain makes selecting a sampling set non-trivial and hard to analyze.

Clustering Video Compression

IQN: An Incremental Quasi-Newton Method with Local Superlinear Convergence Rate

no code implementations2 Feb 2017 Aryan Mokhtari, Mark Eisen, Alejandro Ribeiro

This makes their computational cost per iteration independent of the number of objective functions $n$.

Parsimonious Online Learning with Kernels via Sparse Projections in Function Space

no code implementations13 Dec 2016 Alec Koppel, Garrett Warnell, Ethan Stump, Alejandro Ribeiro

Despite their attractiveness, popular perception is that techniques for nonparametric function approximation do not scale to streaming data due to an intractable growth in the amount of storage they require.

General Classification

Surpassing Gradient Descent Provably: A Cyclic Incremental Method with Linear Convergence Rate

no code implementations1 Nov 2016 Aryan Mokhtari, Mert Gürbüzbalaban, Alejandro Ribeiro

We prove that not only the proposed DIAG method converges linearly to the optimal solution, but also its linear convergence factor justifies the advantage of incremental methods on GD.

Stylometric Analysis of Early Modern Period English Plays

no code implementations18 Oct 2016 Mark Eisen, Santiago Segarra, Gabriel Egan, Alejandro Ribeiro

We first study the similarity of writing styles between Early English playwrights by comparing the profile WANs.

Stochastic Averaging for Constrained Optimization with Application to Online Resource Allocation

no code implementations7 Oct 2016 Tianyi Chen, Aryan Mokhtari, Xin Wang, Alejandro Ribeiro, Georgios B. Giannakis

Existing approaches to resource allocation for nowadays stochastic networks are challenged to meet fast convergence and tolerable delay requirements.

Excisive Hierarchical Clustering Methods for Network Data

no code implementations21 Jul 2016 Gunnar Carlsson, Facundo Mémoli, Alejandro Ribeiro, Santiago Segarra

We introduce two practical properties of hierarchical clustering methods for (possibly asymmetric) network data: excisiveness and linear scale preservation.

Clustering

Hierarchical Clustering of Asymmetric Networks

no code implementations21 Jul 2016 Gunnar Carlsson, Facundo Mémoli, Alejandro Ribeiro, Santiago Segarra

This paper considers networks where relationships between nodes are represented by directed dissimilarities.

Clustering

Admissible Hierarchical Clustering Methods and Algorithms for Asymmetric Networks

no code implementations21 Jul 2016 Gunnar Carlsson, Facundo Mémoli, Alejandro Ribeiro, Santiago Segarra

This paper characterizes hierarchical clustering methods that abide by two previously introduced axioms -- thus, denominated admissible methods -- and proposes tractable algorithms for their implementation.

Clustering

Proximity Without Consensus in Online Multi-Agent Optimization

no code implementations17 Jun 2016 Alec Koppel, Brian M. Sadler, Alejandro Ribeiro

To do so, we depart from the canonical decentralized optimization framework where agreement constraints are enforced, and instead formulate a problem where each agent minimizes a global objective while enforcing network proximity constraints.

Multiagent Systems Systems and Control Computation

A Class of Parallel Doubly Stochastic Algorithms for Large-Scale Learning

no code implementations15 Jun 2016 Aryan Mokhtari, Alec Koppel, Alejandro Ribeiro

Algorithms that are parallel in either of these dimensions exist, but RAPSA is the first attempt at a methodology that is parallel in both the selection of blocks and the selection of elements of the training set.

Image Classification

Decentralized Dynamic Discriminative Dictionary Learning

no code implementations3 May 2016 Alec Koppel, Garrett Warnell, Ethan Stump, Alejandro Ribeiro

We consider discriminative dictionary learning in a distributed online setting, where a network of agents aims to learn a common set of dictionary elements of a feature space and model parameters while sequentially receiving observations.

Dictionary Learning

A Decentralized Quasi-Newton Method for Dual Formulations of Consensus Optimization

no code implementations23 Mar 2016 Mark Eisen, Aryan Mokhtari, Alejandro Ribeiro

The resulting dual D-BFGS method is a fully decentralized algorithm in which nodes approximate curvature information of themselves and their neighbors through the satisfaction of a secant condition.

Second-order methods

Doubly Random Parallel Stochastic Methods for Large Scale Learning

no code implementations22 Mar 2016 Aryan Mokhtari, Alec Koppel, Alejandro Ribeiro

Algorithms that are parallel in either of these dimensions exist, but RAPSA is the first attempt at a methodology that is parallel in both, the selection of blocks and the selection of elements of the training set.

DSA: Decentralized Double Stochastic Averaging Gradient Algorithm

no code implementations13 Jun 2015 Aryan Mokhtari, Alejandro Ribeiro

The decentralized double stochastic averaging gradient (DSA) algorithm is proposed as a solution alternative that relies on: (i) The use of local stochastic averaging gradients.

Optimization and Control

Global Convergence of Online Limited Memory BFGS

no code implementations6 Sep 2014 Aryan Mokhtari, Alejandro Ribeiro

Global convergence of an online (stochastic) limited memory version of the Broyden-Fletcher- Goldfarb-Shanno (BFGS) quasi-Newton method for solving optimization problems with stochastic objectives that arise in large scale machine learning is established.

Authorship Attribution through Function Word Adjacency Networks

no code implementations17 Jun 2014 Santiago Segarra, Mark Eisen, Alejandro Ribeiro

Attribution accuracy is observed to exceed the one achieved by methods that rely on word frequencies alone.

Hierarchical Quasi-Clustering Methods for Asymmetric Networks

no code implementations17 Apr 2014 Gunnar Carlsson, Facundo Mémoli, Alejandro Ribeiro, Santiago Segarra

This paper introduces hierarchical quasi-clustering methods, a generalization of hierarchical clustering for asymmetric networks where the output structure preserves the asymmetry of the input data.

Clustering

A Quasi-Newton Method for Large Scale Support Vector Machines

no code implementations20 Feb 2014 Aryan Mokhtari, Alejandro Ribeiro

This paper adapts a recently developed regularized stochastic version of the Broyden, Fletcher, Goldfarb, and Shanno (BFGS) quasi-Newton method for the solution of support vector machine classification problems.

General Classification

RES: Regularized Stochastic BFGS Algorithm

no code implementations29 Jan 2014 Aryan Mokhtari, Alejandro Ribeiro

Numerical experiments showcase reductions in convergence time relative to stochastic gradient descent algorithms and non-regularized stochastic versions of BFGS.

Second-order methods

Axiomatic Construction of Hierarchical Clustering in Asymmetric Networks

no code implementations31 Jan 2013 Gunnar Carlsson, Facundo Mémoli, Alejandro Ribeiro, Santiago Segarra

Our construction of hierarchical clustering methods is based on defining admissible methods to be those methods that abide by the axioms of value - nodes in a network with two nodes are clustered together at the maximum of the two dissimilarities between them - and transformation - when dissimilarities are reduced, the network may become more clustered but not less.

Clustering

Cannot find the paper you are looking for? You can Submit a new open access paper.