
Federated Learning with Randomized DouglasRachford Splitting Methods
In this paper, we develop two new algorithms, called, FedDR and asyncFed...
read it

Shuffling GradientBased Methods with Momentum
We combine two advanced ideas widely used in optimization for machine le...
read it

Convergence Analysis of HomotopySGD for nonconvex optimization
Firstorder stochastic methods for solving largescale nonconvex optimi...
read it

Hogwild! over Distributed Local Data Sets with Linearly Increasing MiniBatch Sizes
Hogwild! implements asynchronous Stochastic Gradient Descent (SGD) where...
read it

An Optimal Hybrid VarianceReduced Algorithm for Stochastic Composite Nonconvex Optimization
In this note we propose a new variant of the hybrid variancereduced pro...
read it

Asynchronous Federated Learning with Reduced Number of Rounds and with Differential Privacy from Less Aggregated Gaussian Noise
The feasibility of federated learning is highly constrained by the serve...
read it

Hybrid VarianceReduced SGD Algorithms For NonconvexConcave Minimax Problems
We develop a novel variancereduced algorithm to solve a stochastic nonc...
read it

Randomized PrimalDual Algorithms for Composite Convex Minimization with Faster Convergence Rates
We develop two novel randomized primaldual algorithms to solve nonsmoot...
read it

A Hybrid Stochastic Policy Gradient Algorithm for Reinforcement Learning
We propose a novel hybrid stochastic policy gradient estimator by combin...
read it

A Unified Convergence Analysis for ShufflingType Gradient Methods
In this paper, we provide a unified convergence analysis for a class of ...
read it

Stochastic GaussNewton Algorithms for Nonconvex Compositional Optimization
We develop two new stochastic GaussNewton algorithms for solving a clas...
read it

A Newton FrankWolfe Method for Constrained SelfConcordant Minimization
We demonstrate how to scalably solve a class of constrained selfconcord...
read it

Using positive spanning sets to achieve stationarity with the Boosted DC Algorithm
The Difference of Convex function Algorithm (DCA) is widely used for min...
read it

A Hybrid Stochastic Optimization Framework for Stochastic Composite Nonconvex Optimization
In this paper, we introduce a new approach to develop stochastic optimiz...
read it

Hybrid Stochastic Gradient Descent Algorithms for Stochastic Nonconvex Optimization
We introduce a hybrid stochastic estimator to design stochastic gradient...
read it

ProxSARAH: An Efficient Algorithmic Framework for Stochastic Composite Nonconvex Optimization
In this paper, we propose a new stochastic algorithmic framework to solv...
read it

Nonstationary DouglasRachford and alternating direction method of multipliers: adaptive stepsizes and convergence
We revisit the classical DouglasRachford (DR) method for finding a zero...
read it

Smooth PrimalDual Coordinate Descent Algorithms for Nonsmooth Convex Optimization
We propose a new randomized coordinate descent method for a convex optim...
read it

Generalized SelfConcordant Functions: A Recipe for NewtonType Methods
We study the smooth structure of convex functions by generalizing a powe...
read it

Extended GaussNewton and GaussNewtonADMM Algorithms for LowRank Matrix Optimization
We develop a generic GaussNewton (GN) framework for solving a class of ...
read it

Convex blocksparse linear regression with expanders  provably
Sparse matrices are favorable objects in machine learning and optimizati...
read it

A singlephase, proximal pathfollowing framework
We propose a new proximal, pathfollowing framework for a class of const...
read it

Adaptive Smoothing Algorithms for Nonsmooth Composite Convex Minimization
We propose an adaptive smoothing algorithm based on Nesterov's smoothing...
read it

Composite convex minimization involving selfconcordantlike cost functions
The selfconcordantlike property of a smooth convex function is a new a...
read it

A PrimalDual Algorithmic Framework for Constrained Convex Minimization
We present a primaldual algorithmic framework to obtain approximate sol...
read it

Scalable sparse covariance estimation via selfconcordance
We consider the class of convex minimization problems, composed of a sel...
read it

Composite SelfConcordant Minimization
We propose a variable metric framework for minimizing the sum of a self...
read it

A proximal Newton framework for composite minimization: Graph learning without Cholesky decompositions and matrix inversions
We propose an algorithmic framework for convex minimization problems of ...
read it
Quoc TranDinh
is this you? claim profile
Professor Department of Statistics and Operations Research at The University of North Carolina at Chapel Hil