
Tighter Analysis of Alternating Stochastic Gradient Method for Stochastic Nested Problems
Stochastic nested optimization, including stochastic compositional, min...
read it

Learn to Predict Equilibria via Fixed Point Networks
Systems of interacting agents can often be modeled as contextual games, ...
read it

Accelerating Gossip SGD with Periodic Global Averaging
Communication overhead hinders the scalability of largescale distribute...
read it

Feasibilitybased Fixed Point Networks
Inverse problems consist of recovering a signal from a collection of noi...
read it

On the Comparison between Cyclic Sampling and Random Reshuffling
When applying a stochastic/incremental algorithm, one must choose the or...
read it

DecentLaM: Decentralized Momentum SGD for Largebatch Deep Training
The scale of deep learning nowadays calls for efficient distributed trai...
read it

Learning to Optimize: A Primer and A Benchmark
Learning to optimize (L2O) is an emerging approach that leverages machin...
read it

Fixed Point Networks: Implicit Depth Models with JacobianFree Backprop
A growing trend in deep learning replaces fixed depth models by approxim...
read it

Provably Correct Optimization and Exploration with Nonlinear Policies
Policy optimization methods remain a powerful workhorse in empirical Rei...
read it

A ZerothOrder Block Coordinate Descent Algorithm for HugeScale BlackBox Optimization
We consider the zerothorder optimization problem in the hugescale sett...
read it

A SingleTimescale Stochastic Bilevel Optimization Method
Stochastic bilevel optimization generalizes the classic stochastic optim...
read it

CADA: CommunicationAdaptive Distributed Adam
Stochastic gradient descent (SGD) has taken the stage as the primary wor...
read it

Hybrid Federated Learning: Algorithms and Implementation
Federated learning (FL) is a recently proposed distributed machine learn...
read it

SCOBO: SparsityAware Comparison Oracle Based Optimization
We study derivativefree optimization for convex functions where we furt...
read it

Solving Stochastic Compositional Optimization is Nearly as Easy as Solving Stochastic Optimization
Stochastic compositional optimization generalizes classic (noncompositi...
read it

Projecting to Manifolds via Unsupervised Learning
We present a new framework, called adversarial projections, for solving ...
read it

VAFL: a Method of Vertical Asynchronous Federated Learning
Horizontal Federated learning (FL) handles multiclient data that share ...
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

ZerothOrder Regularized Optimization (ZORO): Approximately Sparse Gradients and Adaptive Sampling
We consider the problem of minimizing a highdimensional objective funct...
read it

Provably Efficient Exploration for RL with Unsupervised Learning
We study how to use unsupervised learning for efficient exploration in r...
read it

Safeguarded Learned Convex Optimization
Many applications require repeatedly solving a certain type of optimizat...
read it

LASG: Lazily Aggregated Stochastic Gradients for CommunicationEfficient Distributed Learning
This paper targets solving distributed machine learning problems such as...
read it

Scaled Relative Graph of Normal Matrices
The Scaled Relative Graph (SRG) by Ryu, Hannah, and Yin (arXiv:1902.0978...
read it

Does Knowledge Transfer Always Help to Learn a Better Policy?
One of the key approaches to save samples when learning a policy for a r...
read it

XPipe: Efficient Pipeline Model Parallelism for MultiGPU DNN Training
We propose XPipe, an efficient asynchronous pipeline model parallelism a...
read it

ODE Analysis of Stochastic Gradient Methods with Optimism and Anchoring for Minimax Problems and GANs
Despite remarkable empirical success, the training dynamics of generativ...
read it

PlugandPlay Methods Provably Converge with Properly Trained Denoisers
Plugandplay (PnP) is a nonconvex framework that integrates modern den...
read it

AsyncQVI: AsynchronousParallel QValue Iteration for Reinforcement Learning with NearOptimal Sample Complexity
In this paper, we propose AsyncQVI: AsynchronousParallel Qvalue Iterat...
read it

Markov Chain Block Coordinate Descent
The method of block coordinate gradient descent (BCD) has been a powerfu...
read it

Multilevel Optimal Transport: a Fast Approximation of Wasserstein1 distances
We propose a fast algorithm for the calculation of the Wasserstein1 dis...
read it

On Markov Chain Gradient Descent
Stochastic gradient methods are the workhorse (algorithms) of largescal...
read it

Theoretical Linear Convergence of Unfolded ISTA and its Practical Weights and Thresholds
In recent years, unfolding iterative algorithms as neural networks has b...
read it

LAG: Lazily Aggregated Gradient for CommunicationEfficient Distributed Learning
This paper presents a new class of gradient methods for distributed mach...
read it

Walkman: A CommunicationEfficient RandomWalk Algorithm for Decentralized Optimization
This paper addresses consensus optimization problems in a multiagent ne...
read it

A CommunicationEfficient RandomWalk Algorithm for Decentralized Optimization
This paper addresses consensus optimization problem in a multiagent net...
read it

Redundancy Techniques for Straggler Mitigation in Distributed Optimization and Learning
Performance of distributed optimization and learning systems is bottlene...
read it

Denoising Prior Driven Deep Neural Network for Image Restoration
Deep neural networks (DNNs) have shown very promising results for variou...
read it

Straggler Mitigation in Distributed Optimization Through Data Encoding
Slow running or straggler tasks can significantly reduce computation spe...
read it

Online Convolutional Dictionary Learning
Convolutional sparse representations are a form of sparse representation...
read it

More Iterations per Second, Same Quality  Why Asynchronous Algorithms may Drastically Outperform Traditional Ones
In this paper, we consider the convergence of a very general asynchronou...
read it

A New Use of DouglasRachford Splitting and ADMM for Identifying Infeasible, Unbounded, and Pathological Conic Programs
In this paper, we present a method for identifying infeasible, unbounded...
read it

A Primer on Coordinate Descent Algorithms
This monograph presents a class of algorithms called coordinate descent ...
read it

Coordinate Friendly Structures, Algorithms and Applications
This paper focuses on coordinate update methods, which are useful for so...
read it

ARock: an Algorithmic Framework for Asynchronous Parallel Coordinate Updates
Finding a fixed point to a nonexpansive operator, i.e., x^*=Tx^*, abstra...
read it

A fast patchdictionary method for whole image recovery
Various algorithms have been proposed for dictionary learning. Among tho...
read it

Sparse Recovery via Differential Inclusions
In this paper, we recover sparse signals from their noisy linear measure...
read it

Video Compressive Sensing for Dynamic MRI
We present a video compressive sensing framework, termed ktCSLDS, to ac...
read it

A Matlab Implementation of a Flat Norm Motivated Polygonal Edge Matching Method using a Decomposition of Boundary into Four 1Dimensional Currents
We describe and provide code and examples for a polygonal edge matching ...
read it
Wotao Yin
is this you? claim profile
Applied mathematician and professor in the Mathematics department at the University of California, Los Angeles