Search Results for author:
Found 108 papers, 12 papers with code
Preconditioned Sharpness-Aware Minimization: Unifying Analysis and a Novel Learning Algorithm
Targeting solutions over `flat' regions of the loss landscape, sharpness-aware minimization (SAM) has emerged as a powerful tool to improve generalizability of deep neural network based learning.
Online scalable Gaussian processes with conformal prediction for guaranteed coverage
However, this assumption is usually violated in the online setting, where a prediction set is sought before revealing the true label.
Learning From Crowdsourced Noisy Labels: A Signal Processing Perspective
One of the primary catalysts fueling advances in artificial intelligence (AI) and machine learning (ML) is the availability of massive, curated datasets.
Meta-Learning with Versatile Loss Geometries for Fast Adaptation Using Mirror Descent
Utilizing task-invariant prior knowledge extracted from related tasks, meta-learning is a principled framework that empowers learning a new task especially when data records are limited.
Contractive error feedback for gradient compression
On-device memory concerns in distributed deep learning have become severe due to (i) the growth of model size in multi-GPU training, and (ii) the wide adoption of deep neural networks for federated learning on IoT devices which have limited storage.
3D Reconstruction in Noisy Agricultural Environments: A Bayesian Optimization Perspective for View Planning
3D reconstruction is a fundamental task in robotics that gained attention due to its major impact in a wide variety of practical settings, including agriculture, underwater, and urban environments.
Enhancing Sharpness-Aware Optimization Through Variance Suppression
Sharpness-aware minimization (SAM) has well documented merits in enhancing generalization of deep neural networks, even without sizable data augmentation.
Conic Descent Redux for Memory-Efficient Optimization
Conic programming has well-documented merits in a gamut of signal processing and machine learning tasks.
Scalable Bayesian Meta-Learning through Generalized Implicit Gradients
Meta-learning owns unique effectiveness and swiftness in tackling emerging tasks with limited data.
Weighted Ensembles for Active Learning with Adaptivity
Labeled data can be expensive to acquire in several application domains, including medical imaging, robotics, and computer vision.
Surrogate modeling for Bayesian optimization beyond a single Gaussian process
Tests on synthetic functions and real-world applications showcase the merits of the proposed method.
Time-domain Generalization of Kron Reduction
Kron reduction is a network-reduction method that eliminates nodes with zero current injections from electrical networks operating in sinusoidal steady state.
Fast Inverter Control by Learning the OPF Mapping using Sensitivity-Informed Gaussian Processes
Adjusting inverter injection setpoints for distributed energy resources can be an effective grid control mechanism.
Robust and Adaptive Temporal-Difference Learning Using An Ensemble of Gaussian Processes
Value function approximation is a crucial module for policy evaluation in reinforcement learning when the state space is large or continuous.
Distributionally Robust Semi-Supervised Learning Over Graphs
The data distribution is considered unknown, but lies within a Wasserstein ball centered around empirical data distribution.
Incremental Ensemble Gaussian Processes
Belonging to the family of Bayesian nonparametrics, Gaussian process (GP) based approaches have well-documented merits not only in learning over a rich class of nonlinear functions, but also in quantifying the associated uncertainty.
Heavy Ball Momentum for Conditional Gradient
Conditional gradient, aka Frank Wolfe (FW) algorithms, have well-documented merits in machine learning and signal processing applications.
Detecting adversaries in Crowdsourcing
Despite its successes in various machine learning and data science tasks, crowdsourcing can be susceptible to attacks from dedicated adversaries.
Resonant Beam Communications with Echo Interference Elimination
Resonant beam communications (RBCom) is capable of providing wide bandwidth when using light as the carrier.
End-to-End Transmission Analysis of Simultaneous Wireless Information and Power Transfer using Resonant Beam
Integrating the wireless power transfer (WPT) technology into the wireless communication system has been important for operational cost saving and power-hungry problem solving of electronic devices.
Unveiling Anomalous Edges and Nominal Connectivity of Attributed Networks
Uncovering anomalies in attributed networks has recently gained popularity due to its importance in unveiling outliers and flagging adversarial behavior in a gamut of data and network science applications including {the Internet of Things (IoT)}, finance, security, to list a few.
Learning to Solve the AC-OPF using Sensitivity-Informed Deep Neural Networks
To shift the computational burden from real-time to offline in delay-critical power systems applications, recent works entertain the idea of using a deep neural network (DNN) to predict the solutions of the AC optimal power flow (AC-OPF) once presented load demands.
Bayesian Crowdsourcing with Constraints
Crowdsourcing has emerged as a powerful paradigm for efficiently labeling large datasets and performing various learning tasks, by leveraging crowds of human annotators.
Adversarial Linear Contextual Bandits with Graph-Structured Side Observations
The second algorithm, \texttt{EXP3-LGC-IX}, is developed for a special class of problems, for which the regret is reduced to $\mathcal{O}(\sqrt{\alpha(G)dT\log{K}\log(KT)})$ for both directed as well as undirected feedback graphs.
Enhancing Parameter-Free Frank Wolfe with an Extra Subproblem
Relying on no problem dependent parameters in the step sizes, the convergence rate of ExtraFW for general convex problems is shown to be ${\cal O}(\frac{1}{k})$, which is optimal in the sense of matching the lower bound on the number of solved FW subproblems.
Learning while Respecting Privacy and Robustness to Distributional Uncertainties and Adversarial Data
This robust learning task entails an infinite-dimensional optimization problem, which is challenging.
How Does Momentum Help Frank Wolfe?
We unveil the connections between Frank Wolfe (FW) type algorithms and the momentum in Accelerated Gradient Methods (AGM).
Communication-Efficient Robust Federated Learning Over Heterogeneous Datasets
For strongly convex loss functions, FRPG and LFRPG have provably faster convergence rates than a benchmark robust stochastic aggregation algorithm.
Reinforcement Learning for Caching with Space-Time Popularity Dynamics
With the tremendous growth of data traffic over wired and wireless networks along with the increasing number of rich-media applications, caching is envisioned to play a critical role in next-generation networks.
Pruned Graph Scattering Transforms
Graph convolutional networks (GCNs) have achieved remarkable performance in a variety of network science learning tasks.
Resonant Beam Communications: Principles and Designs
Wireless optical communications (WOC) has carriers up to several hundred terahertz, which offers several advantages, such as ultrawide bandwidth and no electromagnetic interference.
Tensor Graph Convolutional Networks for Multi-relational and Robust Learning
The era of "data deluge" has sparked renewed interest in graph-based learning methods and their widespread applications ranging from sociology and biology to transportation and communications.
Gauss-Newton Unrolled Neural Networks and Data-driven Priors for Regularized PSSE with Robustness
Numerical tests using real load data on the IEEE $118$-bus benchmark system showcase the improved estimation and robustness performance of the proposed scheme compared with several state-of-the-art alternatives.
Efficient and Stable Graph Scattering Transforms via Pruning
The resultant pruning algorithm is guided by a graph-spectrum-inspired criterion, and retains informative scattering features on-the-fly while bypassing the exponential complexity associated with GSTs.
Federated Variance-Reduced Stochastic Gradient Descent with Robustness to Byzantine Attacks
This motivates us to reduce the variance of stochastic gradients as a means of robustifying SGD in the presence of Byzantine attacks.
Finite-Sample Analysis of Decentralized Temporal-Difference Learning with Linear Function Approximation
Motivated by the emerging use of multi-agent reinforcement learning (MARL) in engineering applications such as networked robotics, swarming drones, and sensor networks, we investigate the policy evaluation problem in a fully decentralized setting, using temporal-difference (TD) learning with linear function approximation to handle large state spaces in practice.
A Statistical Learning Approach to Reactive Power Control in Distribution Systems
Taking a statistical learning viewpoint, the input-output relationship between each grid state and the corresponding optimal reactive power control is parameterized in the present work by a deep neural network, whose unknown weights are learned offline by minimizing the power loss over a number of historical and simulated training pairs.
GraphSAC: Detecting anomalies in large-scale graphs
Alleviating this limitation, GraphSAC randomly draws subsets of nodes, and relies on graph-aware criteria to judiciously filter out sets contaminated by anomalous nodes, before employing a semi-supervised learning (SSL) module to estimate nominal label distributions per node.
Edge Dithering for Robust Adaptive Graph Convolutional Networks
Graph convolutional networks (GCNs) are vulnerable to perturbations of the graph structure that are either random, or, adversarially designed.
Adaptive Step Sizes in Variance Reduction via Regularization
The main goal of this work is equipping convex and nonconvex problems with Barzilai-Borwein (BB) step size.
Communication-Efficient Distributed Learning via Lazily Aggregated Quantized Gradients
The present paper develops a novel aggregated gradient approach for distributed machine learning that adaptively compresses the gradient communication.
A Multistep Lyapunov Approach for Finite-Time Analysis of Biased Stochastic Approximation
Motivated by the widespread use of temporal-difference (TD-) and Q-learning algorithms in reinforcement learning, this paper studies a class of biased stochastic approximation (SA) procedures under a mild "ergodic-like" assumption on the underlying stochastic noise sequence.
A Variational Bayes Approach to Adaptive Radio Tomography
Radio tomographic imaging (RTI) is an emerging technology for localization of physical objects in a geographical area covered by wireless networks.
Almost Tune-Free Variance Reduction
Then a simple yet effective means to adjust the number of iterations per inner loop is developed to enhance the merits of the proposed averaging schemes and BB step sizes.
Unsupervised Ensemble Classification with Sequential and Networked Data
data, the present work introduces an unsupervised scheme for learning from ensembles of classifiers in the presence of data dependencies.
Generalization error bounds for kernel matrix completion and extrapolation
This paper analyzes the generalization error of such approaches, and presents numerical tests confirming the theoretical results.
On the Convergence of SARAH and Beyond
For convex problems, when adopting an $n$-dependent step size, the complexity of L2S is ${\cal O}(n+ \sqrt{n}/\epsilon)$; while for more frequently adopted $n$-independent step size, the complexity is ${\cal O}(n+ n/\epsilon)$.
Minimum Uncertainty Based Detection of Adversaries in Deep Neural Networks
The effectiveness of the novel detectors in the context of competing alternatives is highlighted through extensive tests for various types of adversarial attacks with variable levels of strength.
Deep Reinforcement Learning for Adaptive Caching in Hierarchical Content Delivery Networks
To handle the large continuous state space, a scalable deep reinforcement learning approach is pursued.
Reinforcement Learning for Adaptive Caching with Dynamic Storage Pricing
Under this generic formulation, first by considering stationary distributions for the costs and file popularities, an efficient reinforcement learning-based solver known as value iteration algorithm can be used to solve the emerging optimization problem.
Communication-Efficient Policy Gradient Methods for Distributed Reinforcement Learning
This paper deals with distributed policy optimization in reinforcement learning, which involves a central controller and a group of learners.
Online Graph-Adaptive Learning with Scalability and Privacy
Moreover, new nodes can emerge over time, which can necessitate real-time evaluation of their nodal attributes.
Node Embedding with Adaptive Similarities for Scalable Learning over Graphs
Moreover, an algorithmic scheme is proposed for training the model parameters effieciently and in an unsupervised manner.
Real-time Power System State Estimation and Forecasting via Deep Neural Networks
To bypass these hurdles, this paper advocates deep neural networks (DNNs) for real-time power system monitoring.
RSA: Byzantine-Robust Stochastic Aggregation Methods for Distributed Learning from Heterogeneous Datasets
In this paper, we propose a class of robust stochastic subgradient methods for distributed learning from heterogeneous datasets at presence of an unknown number of Byzantine workers.
A Recurrent Graph Neural Network for Multi-Relational Data
The era of data deluge has sparked the interest in graph-based learning methods in a number of disciplines such as sociology, biology, neuroscience, or engineering.
Coupled Graphs and Tensor Factorization for Recommender Systems and Community Detection
The resulting community detection approach is successful even when some links in the graphs are missing.
Learning ReLU Networks on Linearly Separable Data: Algorithm, Optimality, and Generalization
In this context, the problem of learning a two-layer ReLU network is approached in a binary classification setting, where the data are linearly separable and a hinge loss criterion is adopted.
Matrix completion and extrapolation via kernel regression
Matrix completion and extrapolation (MCEX) are dealt with here over reproducing kernel Hilbert spaces (RKHSs) in order to account for prior information present in the available data.
Bandit Online Learning with Unknown Delays
This paper deals with bandit online learning problems involving feedback of unknown delay that can emerge in multi-armed bandit (MAB) and bandit convex optimization (BCO) settings.
LAG: Lazily Aggregated Gradient for Communication-Efficient Distributed Learning
This paper presents a new class of gradient methods for distributed machine learning that adaptively skip the gradient calculations to learn with reduced communication and computation.
Semi-Blind Inference of Topologies and Dynamical Processes over Graphs
Alleviating the limited flexibility of existing approaches, this work advocates structural models for graph processes and develops novel algorithms for joint inference of the network topology and processes from partial nodal observations.
Nonlinear Dimensionality Reduction for Discriminative Analytics of Multiple Datasets
Under certain conditions, dPCA is proved to be least-squares optimal in recovering the component vector unique to the target data relative to background data.
Secure Mobile Edge Computing in IoT via Collaborative Online Learning
To accommodate heterogeneous tasks in Internet of Things (IoT), a new communication and computing paradigm termed mobile edge computing emerges that extends computing services from the cloud to edge, but at the same time exposes new challenges on security.
Adaptive Bayesian Radio Tomography
Key to success of RTI is to model accurately the shadowing effects as the bi-dimensional integral of the SLF scaled by a weight function, which is estimated using regularized regression.
Signal Processing Applications
Adaptive Diffusions for Scalable Learning over Graphs
Diffusion-based classifiers such as those relying on the Personalized PageRank and the Heat kernel, enjoy remarkable classification accuracy at modest computational requirements.
Canonical Correlation Analysis of Datasets with a Common Source Graph
Canonical correlation analysis (CCA) is a powerful technique for discovering whether or not hidden sources are commonly present in two (or more) datasets.
Nonlinear Dimensionality Reduction on Graphs
The novel framework encompasses most of the existing dimensionality reduction methods, but it is also capable of capturing and preserving possibly nonlinear correlations that are ignored by linear methods.
Random Feature-based Online Multi-kernel Learning in Environments with Unknown Dynamics
To further boost performance in dynamic environments, an adaptive multi-kernel learning scheme (termed AdaRaker) is developed.
Blind Multiclass Ensemble Classification
The rising interest in pattern recognition and data analytics has spurred the development of innovative machine learning algorithms and tools.
Kernel-based Inference of Functions over Graphs
The study of networks has witnessed an explosive growth over the past decades with several ground-breaking methods introduced.
Inference of Spatio-Temporal Functions over Graphs via Multi-Kernel Kriged Kalman Filtering
Inference of space-time varying signals on graphs emerges naturally in a plethora of network science related applications.
DPCA: Dimensionality Reduction for Discriminative Analytics of Multiple Large-Scale Datasets
Principal component analysis (PCA) has well-documented merits for data extraction and dimensionality reduction.
Bandit Convex Optimization for Scalable and Dynamic IoT Management
Tailored for such human-in-the-loop systems where the loss functions are hard to model, a family of bandit online saddle-point (BanSaP) schemes are developed, which adaptively adjust the online operations based on (possibly multiple) bandit feedback of the loss functions, and the changing environment.
Sketched Subspace Clustering
The immense amount of daily generated and communicated data presents unique challenges in their processing.
Optimal and Scalable Caching for 5G Using Reinforcement Learning of Space-time Popularities
To intelligently prefetch, each SB must learn what and when to cache, while taking into account SB memory limitations, the massive number of available contents, the unknown popularity profiles, as well as the space-time popularity dynamics of user file requests.
Networking and Internet Architecture
Solving Almost all Systems of Random Quadratic Equations
This paper deals with finding an $n$-dimensional solution $x$ to a system of quadratic equations of the form $y_i=|\langle{a}_i, x\rangle|^2$ for $1\le i \le m$, which is also known as phase retrieval and is NP-hard in general.
Data-adaptive Active Sampling for Efficient Graph-Cognizant Classification
Leveraging the graph for classification builds on the premise that labels across neighboring nodes are correlated according to a categorical Markov random field (MRF).
An Online Convex Optimization Approach to Dynamic Network Resource Allocation
Performance of an online algorithm in this setting is assessed by: i) the difference of its losses relative to the best dynamic solution with one-slot-ahead information of the loss function and the constraint (that is here termed dynamic regret); and, ii) the accumulated amount of constraint violations (that is here termed dynamic fit).
Randomized Block Frank-Wolfe for Convergent Large-Scale Learning
To circumvent the limitations of existing methods, the present work develops step sizes for RB-FW that enable a flexible selection of the number of blocks to update per iteration while ensuring convergence and feasibility of the iterates.
Kernel-based Reconstruction of Space-time Functions on Dynamic Graphs
Graph-based methods pervade the inference toolkits of numerous disciplines including sociology, biology, neuroscience, physics, chemistry, and engineering.
Sparse Phase Retrieval via Truncated Amplitude Flow
Upon formulating sparse PR as an amplitude-based nonconvex optimization task, SPARTA works iteratively in two stages: In stage one, the support of the underlying sparse signal is recovered using an analytically well-justified rule, and subsequently, a sparse orthogonality-promoting initialization is obtained via power iterations restricted on the support; and, in the second stage, the initialization is successively refined by means of hard thresholding based gradient-type iterations.
Information Theory Information Theory Optimization and Control
Solving Large-scale Systems of Random Quadratic Equations via Stochastic Truncated Amplitude Flow
A novel approach termed \emph{stochastic truncated amplitude flow} (STAF) is developed to reconstruct an unknown $n$-dimensional real-/complex-valued signal $\bm{x}$ from $m$ `phaseless' quadratic equations of the form $\psi_i=|\langle\bm{a}_i,\bm{x}\rangle|$.
Tensor Decompositions for Identifying Directed Graph Topologies and Tracking Dynamic Networks
The present paper advocates a novel SEM-based topology inference approach that entails factorization of a three-way tensor, constructed from the observed nodal data, using the well-known parallel factor (PARAFAC) decomposition.
Nonlinear Structural Vector Autoregressive Models for Inferring Effective Brain Network Connectivity
To unify these complementary perspectives, linear structural vector autoregressive models (SVARMs) that leverage both contemporaneous and time-lagged nodal data have recently been put forth.
Stochastic Averaging for Constrained Optimization with Application to Online Resource Allocation
Existing approaches to resource allocation for nowadays stochastic networks are challenged to meet fast convergence and tolerable delay requirements.
Online Categorical Subspace Learning for Sketching Big Data with Misses
The deterministic Probit and Tobit models treat data as quantized values of an analog-valued process lying in a low-dimensional subspace, while the probabilistic Logit model relies on low dimensionality of the data log-likelihood ratios.
Tracking Tensor Subspaces with Informative Random Sampling for Real-Time MR Imaging
Alteranating majorization minimization is adopted to develop online algorithms that recursively procure the reconstruction upon arrival of a new undersampled $k$-space frame.
Tracking Switched Dynamic Network Topologies from Information Cascades
Contagions such as the spread of popular news stories, or infectious diseases, propagate in cascades over dynamic networks with unobservable topologies.
Learning Power Spectrum Maps from Quantized Power Measurements
Power spectral density (PSD) maps providing the distribution of RF power across space and frequency are constructed using power measurements collected by a network of low-cost sensors.
Solving Systems of Random Quadratic Equations via Truncated Amplitude Flow
This paper presents a new algorithm, termed \emph{truncated amplitude flow} (TAF), to recover an unknown vector $\bm{x}$ from a system of quadratic equations of the form $y_i=|\langle\bm{a}_i,\bm{x}\rangle|^2$, where $\bm{a}_i$'s are given random measurement vectors.
Kernel-based Reconstruction of Graph Signals
A number of SPoG notions such as bandlimitedness, graph filters, and the graph Fourier transform are naturally accommodated in the kernel framework.
Kernel-Based Structural Equation Models for Topology Identification of Directed Networks
Interestingly, pursuit of the novel kernel-based approach yields a convex regularized estimator that promotes edge sparsity, and is amenable to proximal-splitting optimization methods.
Large-scale Kernel-based Feature Extraction via Budgeted Nonlinear Subspace Tracking
Kernel-based methods enjoy powerful generalization capabilities in handling a variety of learning tasks.
Large-scale subspace clustering using sketching and validation
At the heart of SkeVa-SC lies a randomized scheme for approximating the underlying probability density function of the observed data by kernel smoothing arguments.
Online Censoring for Large-Scale Regressions with Application to Streaming Big Data
Linear regression is arguably the most prominent among statistical inference methods, popular both for its simplicity as well as its broad applicability.
Joint community and anomaly tracking in dynamic networks
Efficient tracking algorithms suitable for both online and decentralized operation are developed.
Decentralized learning for wireless communications and networking
This chapter deals with decentralized learning algorithms for in-network processing of graph-valued data.
Per-Block-Convex Data Modeling by Accelerated Stochastic Approximation
Applications involving dictionary learning, non-negative matrix factorization, subspace clustering, and parallel factor tensor decomposition tasks motivate well algorithms for per-block-convex and non-smooth optimization problems.
Sketch and Validate for Big Data Clustering
In response to the need for learning tools tuned to big data analytics, the present paper introduces a framework for efficient clustering of huge sets of (possibly high-dimensional) data.
Online Energy Price Matrix Factorization for Power Grid Topology Tracking
Grid security and open markets are two major smart grid goals.
Backhaul-Constrained Multi-Cell Cooperation Leveraging Sparsity and Spectral Clustering
Dynamic clustered cooperation, where the sparse equalizer and the cooperation clusters are jointly determined, is solved via alternating minimization based on spectral clustering and group-sparse regression.
Subspace Learning and Imputation for Streaming Big Data Matrices and Tensors
In this context, the present paper permeates benefits from rank minimization to scalable imputation of missing data, via tracking low-dimensional subspaces and unraveling latent (possibly multi-way) structure from \emph{incomplete streaming} data.
Embedding Graphs under Centrality Constraints for Network Visualization
Visual rendering of graphs is a key task in the mapping of complex network data.
Grid Topology Identification using Electricity Prices
The potential of recovering the topology of a grid using solely publicly available market data is explored here.
Electricity Market Forecasting via Low-Rank Multi-Kernel Learning
The smart grid vision entails advanced information technology and data analytics to enhance the efficiency, sustainability, and economics of the power grid infrastructure.
Distributed Robust Power System State Estimation
Deregulation of energy markets, penetration of renewables, advanced metering capabilities, and the urge for situational awareness, all call for system-wide power system state estimation (PSSE).
