Search Results for author:
Found 49 papers, 5 papers with code
Network Games Induced Prior for Graph Topology Learning
We draw theoretical insights on the optimal graph structure of the bilevel program and show that they agree with the topology in several man-made networks.
Fully Stochastic Primal-dual Gradient Algorithm for Non-convex Optimization on Random Graphs
Stochastic decentralized optimization algorithms often suffer from issues such as synchronization overhead and intermittent communication.
Getting More Juice Out of the SFT Data: Reward Learning from Human Demonstration Improves SFT for LLM Alignment
State-of-the-art techniques such as Reinforcement Learning from Human Feedback (RLHF) often consist of two stages: 1) supervised fine-tuning (SFT), where the model is fine-tuned by learning from human demonstration data; 2) Preference learning, where preference data is used to learn a reward model, which is in turn used by a reinforcement learning (RL) step to fine-tune the model.
Dual-Delayed Asynchronous SGD for Arbitrarily Heterogeneous Data
We consider the distributed learning problem with data dispersed across multiple workers under the orchestration of a central server.
On Detecting Low-pass Graph Signals under Partial Observations
We propose a detector that certifies whether the partially observed graph signals are low pass filtered, without requiring the graph topology knowledge.
Clipped SGD Algorithms for Privacy Preserving Performative Prediction: Bias Amplification and Remedies
This paper studies the convergence properties of these algorithms in a performative prediction setting, where the data distribution may shift due to the deployed prediction model.
EMC$^2$: Efficient MCMC Negative Sampling for Contrastive Learning with Global Convergence
We follow the global contrastive learning loss as introduced in SogCLR, and propose EMC$^2$ which utilizes an adaptive Metropolis-Hastings subroutine to generate hardness-aware negative samples in an online fashion during the optimization.
Linear Speedup of Incremental Aggregated Gradient Methods on Streaming Data
This paper considers a type of incremental aggregated gradient (IAG) method for large-scale distributed optimization.
Blind Graph Matching Using Graph Signals
Our analysis shows that the blind matching outcome converges to the result obtained with known graph topologies when the signal sampling size is large and the signal noise is small.
Detecting Low Pass Graph Signals via Spectral Pattern: Sampling Complexity and Applications
This paper proposes a blind detection problem for low pass graph signals.
Clustering of Time-Varying Graphs Based on Temporal Label Smoothness
In this paper, we formulate a node clustering of time-varying graphs as an optimization problem based on spectral clustering, with a smoothness constraint of the node labels.
Stochastic Approximation Beyond Gradient for Signal Processing and Machine Learning
Stochastic Approximation (SA) is a classical algorithm that has had since the early days a huge impact on signal processing, and nowadays on machine learning, due to the necessity to deal with a large amount of data observed with uncertainties.
Product Graph Learning from Multi-attribute Graph Signals with Inter-layer Coupling
This paper considers learning a product graph from multi-attribute graph signals.
Online Inference for Mixture Model of Streaming Graph Signals with Non-White Excitation
We study a mixture model of filtered low pass graph signals with possibly non-white and low-rank excitation.
DoCoM: Compressed Decentralized Optimization with Near-Optimal Sample Complexity
This paper proposes the Doubly Compressed Momentum-assisted stochastic gradient tracking algorithm $\texttt{DoCoM}$ for communication-efficient decentralized optimization.
On the Stability of Low Pass Graph Filter With a Large Number of Edge Rewires
The stability of a graph filter characterizes the effect of topology perturbation on the output of a graph filter, a fundamental building block for GCNs.
An Empirical Study on Compressed Decentralized Stochastic Gradient Algorithms with Overparameterized Models
In this work, we present an empirical analysis on the performance of compressed decentralized stochastic gradient (DSG) algorithms with overparameterized NNs.
Inducing Equilibria via Incentives: Simultaneous Design-and-Play Ensures Global Convergence
To regulate a social system comprised of self-interested agents, economic incentives are often required to induce a desirable outcome.
Detecting Central Nodes from Low-rank Excited Graph Signals via Structured Factor Analysis
For general low pass graph filter, we show that the graph signals can be described by a structured factor model featuring the product between a low-rank plus sparse factor and an unstructured factor.
Robust Distributed Optimization With Randomly Corrupted Gradients
In this paper, we propose a first-order distributed optimization algorithm that is provably robust to Byzantine failures-arbitrary and potentially adversarial behavior, where all the participating agents are prone to failure.
Tight High Probability Bounds for Linear Stochastic Approximation with Fixed Stepsize
This family of methods arises in many machine learning tasks and is used to obtain approximate solutions of a linear system $\bar{A}\theta = \bar{b}$ for which $\bar{A}$ and $\bar{b}$ can only be accessed through random estimates $\{({\bf A}_n, {\bf b}_n): n \in \mathbb{N}^*\}$.
A Near-Optimal Algorithm for Stochastic Bilevel Optimization via Double-Momentum
We focus on bilevel problems where the lower level subproblem is strongly-convex and the upper level objective function is smooth.
On the Stability of Random Matrix Product with Markovian Noise: Application to Linear Stochastic Approximation and TD Learning
This paper studies the exponential stability of random matrix products driven by a general (possibly unbounded) state space Markov chain.
Identifying First-order Lowpass Graph Signals using Perron Frobenius Theorem
Utilizing this observation, we develop a simple detector that answers if a given data set is produced by a first-order lowpass graph filter.
Provably Efficient Neural GTD for Off-Policy Learning
This paper studies a gradient temporal difference (GTD) algorithm using neural network (NN) function approximators to minimize the mean squared Bellman error (MSBE).
A Stochastic Path Integral Differential EstimatoR Expectation Maximization Algorithm
The Expectation Maximization (EM) algorithm is of key importance for inference in latent variable models including mixture of regressors and experts, missing observations.
A Stochastic Path-Integrated Differential EstimatoR Expectation Maximization Algorithm
The Expectation Maximization (EM) algorithm is of key importance for inference in latent variable models including mixture of regressors and experts, missing observations.
Geom-SPIDER-EM: Faster Variance Reduced Stochastic Expectation Maximization for Nonconvex Finite-Sum Optimization
The Expectation Maximization (EM) algorithm is a key reference for inference in latent variable models; unfortunately, its computational cost is prohibitive in the large scale learning setting.
On the Convergence of Consensus Algorithms with Markovian Noise and Gradient Bias
This rate is comparable to the best known performances of SA in a centralized setting with a non-convex potential function.
A User Guide to Low-Pass Graph Signal Processing and its Applications
The notion of graph filters can be used to define generative models for graph data.
A Two-Timescale Framework for Bilevel Optimization: Complexity Analysis and Application to Actor-Critic
Bilevel optimization is a class of problems which exhibit a two-level structure, and its goal is to minimize an outer objective function with variables which are constrained to be the optimal solution to an (inner) optimization problem.
Convergence Analysis of Riemannian Stochastic Approximation Schemes
This paper analyzes the convergence for a large class of Riemannian stochastic approximation (SA) schemes, which aim at tackling stochastic optimization problems.
Finite Time Analysis of Linear Two-timescale Stochastic Approximation with Markovian Noise
Our bounds show that there is no discrepancy in the convergence rate between Markovian and martingale noise, only the constants are affected by the mixing time of the Markov chain.
Distributed Learning in the Non-Convex World: From Batch to Streaming Data, and Beyond
In particular, we {provide a selective review} about the recent techniques developed for optimizing non-convex models (i. e., problem classes), processing batch and streaming data (i. e., data types), over the networks in a distributed manner (i. e., communication and computation paradigm).
Variance Reduced Policy Evaluation with Smooth Function Approximation
Policy evaluation with smooth and nonlinear function approximation has shown great potential for reinforcement learning.
On the Global Convergence of (Fast) Incremental Expectation Maximization Methods
To alleviate this problem, Neal and Hinton have proposed an incremental version of the EM (iEM) in which at each iteration the conditional expectation of the latent data (E-step) is updated only for a mini-batch of observations.
Spectral partitioning of time-varying networks with unobserved edges
We discuss a variant of `blind' community detection, in which we aim to partition an unobserved network from the observation of a (dynamical) graph signal defined on the network.
Non-asymptotic Analysis of Biased Stochastic Approximation Scheme
We illustrate these settings with the online EM algorithm and the policy-gradient method for average reward maximization in reinforcement learning.
Block-Randomized Stochastic Proximal Gradient for Low-Rank Tensor Factorization
In this work, we propose a stochastic optimization framework for large-scale CPD with constraints/regularizations.
Low-rank Interaction with Sparse Additive Effects Model for Large Data Frames
In this paper, we introduce a low-rank interaction and sparse additive effects (LORIS) model which combines matrix regression on a dictionary and low-rank design, to estimate main effects and interactions simultaneously.
Blind Community Detection from Low-rank Excitations of a Graph Filter
The paper shows that communities can be detected by applying a spectral method to the covariance matrix of graph signals.
Multi-Agent Reinforcement Learning via Double Averaging Primal-Dual Optimization
Despite the success of single-agent reinforcement learning, multi-agent reinforcement learning (MARL) remains challenging due to complex interactions between agents.
Multi-agent Reinforcement Learning
reinforcement-learning
+2
Accelerating Incremental Gradient Optimization with Curvature Information
This paper studies an acceleration technique for incremental aggregated gradient ({\sf IAG}) method through the use of \emph{curvature} information for solving strongly convex finite sum optimization problems.
SUCAG: Stochastic Unbiased Curvature-aided Gradient Method for Distributed Optimization
We propose and analyze a new stochastic gradient method, which we call Stochastic Unbiased Curvature-aided Gradient (SUCAG), for finite sum optimization problems.
Curvature-aided Incremental Aggregated Gradient Method
We propose a new algorithm for finite sum optimization which we call the curvature-aided incremental aggregated gradient (CIAG) method.
RIDS: Robust Identification of Sparse Gene Regulatory Networks from Perturbation Experiments
To overcome this challenge, we develop the Robust IDentification of Sparse networks (RIDS) method that reconstructs the GRN from a small number of perturbation experiments.
Decentralized Frank-Wolfe Algorithm for Convex and Non-convex Problems
The convergence of the proposed algorithm is studied by viewing the decentralized algorithm as an inexact FW algorithm.
Active Sensing of Social Networks
The model used for the regression is based on the steady state equation in the linear DeGroot model under the influence of stubborn agents, i. e., agents whose opinions are not influenced by their neighbors.
On the Online Frank-Wolfe Algorithms for Convex and Non-convex Optimizations
With a strongly convex stochastic cost and when the optimal solution lies in the interior of the constraint set or the constraint set is a polytope, the regret bound and anytime optimality are shown to be ${\cal O}( \log^3 T / T )$ and ${\cal O}( \log^2 T / T)$, respectively, where $T$ is the number of rounds played.
