
Imitation Privacy
In recent years, there have been many cloudbased machine learning servi...
read it

A TwoTimescale Framework for Bilevel Optimization: Complexity Analysis and Application to ActorCritic
This paper analyzes a twotimescale stochastic algorithm for a class of ...
read it

Understanding Gradient Clipping in Private SGD: A Geometric Perspective
Deep learning models are increasingly popular in many machine learning a...
read it

Private Stochastic NonConvex Optimization: Adaptive Algorithms and Tighter Generalization Bounds
We study differentially private (DP) algorithms for stochastic nonconve...
read it

On the Divergence of Decentralized NonConvex Optimization
We study a generic class of decentralized algorithms in which N agents j...
read it

FedPD: A Federated Learning Framework with Optimal Rates and Adaptivity to NonIID Data
Federated Learning (FL) has become a popular paradigm for learning from ...
read it

Distributed Learning in the NonConvex World: From Batch to Streaming Data, and Beyond
Distributed learning has become a critical enabler of the massively conn...
read it

A Communication Efficient Vertical Federated Learning Framework
One critical challenge for applying today's Artificial Intelligence (AI)...
read it

Dense Recurrent Neural Networks for Inverse Problems: HistoryCognizant Unrolling of Optimization Algorithms
Inverse problems in medical imaging applications incorporate domainspec...
read it

ZOAdaMM: ZerothOrder Adaptive Momentum Method for BlackBox Optimization
The adaptive momentum method (AdaMM), which uses past gradients to updat...
read it

Improving the Sample and Communication Complexity for Decentralized NonConvex Optimization: A Joint Gradient Estimation and Tracking Approach
Many modern largescale machine learning problems benefit from decentral...
read it

On the Global Convergence of ActorCritic: A Case for Linear Quadratic Regulator with Ergodic Cost
Despite the empirical success of the actorcritic algorithm, its theoret...
read it

SNAP: Finding Approximate SecondOrder Stationary Solutions Efficiently for Nonconvex Linearly Constrained Problems
This paper proposes lowcomplexity algorithms for finding approximate se...
read it

Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective
Graph neural networks (GNNs) which apply the deep neural networks to gra...
read it

Learned Conjugate Gradient Descent Network for Massive MIMO Detection
In this work, we consider the use of modeldriven deep learning techniqu...
read it

Distributed Training with Heterogeneous Data: Bridging Median and Mean Based Algorithms
Recently, there is a growing interest in the study of medianbased algor...
read it

Hybrid Block Successive Approximation for OneSided NonConvex MinMax Problems: Algorithms and Applications
The minmax problem, also known as the saddle point problem, is a class ...
read it

Multiuser Video Streaming Rate Adaptation: A Physical Layer ResourceAware Deep Reinforcement Learning Approach
We consider a multiuser video streaming service optimization problem ov...
read it

On the Global Convergence of Imitation Learning: A Case for Linear Quadratic Regulator
We study the global convergence of generative adversarial imitation lear...
read it

On the Convergence of A Class of AdamType Algorithms for NonConvex Optimization
This paper studies a class of adaptive gradient based momentum algorithm...
read it

MultiAgent Reinforcement Learning via Double Averaging PrimalDual Optimization
Despite the success of singleagent reinforcement learning, multiagent ...
read it

Structured SUMCOR Multiview Canonical Correlation Analysis for LargeScale Data
The sumofcorrelations (SUMCOR) formulation of generalized canonical co...
read it

Distributed NonConvex FirstOrder Optimization and Information Processing: Lower Complexity Bounds and Rate Optimal Algorithms
We consider a class of distributed nonconvex optimization problems ofte...
read it

MirrorProx SCA Algorithm for Multicast Beamforming and Antenna Selection
This paper considers the (NP)hard problem of joint multicast beamformin...
read it

On the Sublinear Convergence of Randomly Perturbed Alternating Gradient Descent to Second Order Stationary Solutions
The alternating gradient descent (AGD) is a simple but popular algorithm...
read it

Gradient PrimalDual Algorithm Converges to SecondOrder Stationary Solutions for Nonconvex Distributed Optimization
In this work, we study two firstorder primaldual based algorithms, the...
read it

Spectral Efficiency Optimization For Millimeter Wave MultiUser MIMO Systems
As a key enabling technology for 5G wireless, millimeter wave (mmWave) c...
read it

Penalty Dual Decomposition Method For Nonsmooth Nonconvex Optimization
Many contemporary signal processing, machine learning and wireless commu...
read it

Zeroth Order Nonconvex MultiAgent Optimization over Networks
In this paper we consider distributed optimization problems over a multi...
read it

A Nonconvex Splitting Method for Symmetric Nonnegative Matrix Factorization: Convergence Analysis and Optimality
Symmetric nonnegative matrix factorization (SymNMF) has important applic...
read it

On Faster Convergence of Cyclic Block Coordinate Descenttype Methods for Strongly Convex Minimization
The cyclic block coordinate descenttype (CBCDtype) methods, which perf...
read it

Scalable and Flexible Multiview MAXVAR Canonical Correlation Analysis
Generalized canonical correlation analysis (GCCA) aims at finding latent...
read it

A First Order Free Lunch for SQRTLasso
Many statistical machine learning techniques sacrifice convenient comput...
read it

NESTT: A Nonconvex PrimalDual Splitting Method for Distributed and Stochastic Optimization
We study a stochastic and distributed algorithm for nonconvex problems w...
read it

Alternating direction method of multipliers for penalized zerovariance discriminant analysis
We consider the task of classification in the high dimensional setting w...
read it