82 citations · 546 across the 65 of their papers we have counts for
49 papers · 1 filter
First-order Policy Optimization for Robust Policy Evaluation
Yan Li, Guanghui Lan
We adopt a policy optimization viewpoint towards policy evaluation for robust Markov decision process with -rectangular ambiguity sets. The developed method, named firs…
Accelerated stochastic approximation with state-dependent noise
Sasila Ilandarideva, Anatoli Juditsky, Guanghui Lan +1
We consider a class of stochastic smooth convex optimization problems under rather general assumptions on the noise in the stochastic gradient observation. As opposed to the classi…
Numerical Methods for Convex Multistage Stochastic Optimization
Guanghui Lan, Alexander Shapiro
Optimization problems involving sequential decisions in a stochastic environment were studied in Stochastic Programming (SP), Stochastic Optimal Control (SOC) and Markov Decision P…
Dual dynamic programming for stochastic programs over an infinite horizon
Caleb Ju, Guanghui Lan
We consider solving stochastic programs over an infinite horizon. By leveraging the stationarity of the problem, we develop a novel continually-exploring infinite-horizon explorati…
Solving Convex Smooth Function Constrained Optimization Is Almost As Easy As Unconstrained Optimization
Zhe Zhang, Guanghui Lan
While Nesterov's Accelerated Gradient Descent (AGD) efficiently solves constrained problems when the constraint set $X \subseteq \bbr^n$ is simple and easy to project onto, it rema…
Projection-Free Functional Constrained Optimization for Risk Aversion and Sparsity Control
Yi Cheng, Guanghui Lan, Saeed Masiha +1
We study projection-free methods for functional constrained optimization with convex or smooth nonconvex objectives. Such problems arise in applications such as portfolio optimizat…
Level Constrained First Order Methods for Function Constrained Optimization
Digvijay Boob, Qi Deng, Guanghui Lan
We present a new feasible proximal gradient method for constrained optimization where both the objective and constraint functions are given by the summation of a smooth, possibly n…
Optimal Methods for Convex Risk Averse Distributed Optimization
Guanghui Lan, Zhe Zhang
This paper studies the communication complexity of convex risk-averse optimization over a network. The problem generalizes the well-studied risk-neutral finite-sum distributed opti…
Mirror-prox sliding methods for solving a class of monotone variational inequalities
Guanghui Lan, Yuyuan Ouyang
In this paper we propose new algorithms for solving a class of structured monotone variational inequality (VI) problems over compact feasible sets. By identifying the gradient comp…
Faster Algorithm and Sharper Analysis for Constrained Markov Decision Process
Tianjiao Li, Ziwei Guan, Shaofeng Zou +3
The problem of constrained Markov decision process (CMDP) is investigated, where an agent aims to maximize the expected accumulated discounted reward subject to multiple constraint…
Graph topology invariant gradient and sampling complexity for decentralized and stochastic optimization
Guanghui Lan, Yuyuan Ouyang, Yi Zhou
One fundamental problem in decentralized multi-agent optimization is the trade-off between gradient/sampling complexity and communication complexity. We propose new algorithms whos…
Optimal Algorithms for Convex Nested Stochastic Composite Optimization
Zhe Zhang, Guanghui Lan
Recently, convex nested stochastic composite optimization (NSCO) has received considerable attention for its applications in reinforcement learning and risk-averse optimization. Th…
Simple and optimal methods for stochastic variational inequalities, II: Markovian noise and policy evaluation in reinforcement learning
Georgios Kotsalis, Guanghui Lan, Tianjiao Li
The focus of this paper is on stochastic variational inequalities (VI) under Markovian noise. A prominent application of our algorithmic developments is the stochastic policy evalu…
Simple and optimal methods for stochastic variational inequalities, I: operator extrapolation
Georgios Kotsalis, Guanghui Lan, Tianjiao Li
In this paper we first present a novel operator extrapolation (OE) method for solving deterministic variational inequality (VI) problems. Similar to the gradient (operator) project…
A Feasible Level Proximal Point Method for Nonconvex Sparse Constrained Optimization
Digvijay Boob, Qi Deng, Guanghui Lan +1
Nonconvex sparse models have received significant attention in high-dimensional machine learning. In this paper, we study a new model consisting of a general convex or nonconvex ob…
Conditional Gradient Methods for Convex Optimization with General Affine and Nonlinear Constraints
Guanghui Lan, Edwin Romeijn, Zhiqiang Zhou
Conditional gradient methods have attracted much attention in both machine learning and optimization communities recently. These simple methods can guarantee the generation of spar…
Convex optimization for finite horizon robust covariance control of linear stochastic systems
Georgios Kotsalis, Guanghui Lan, Arkadi Nemirovski
This work addresses the finite-horizon robust covariance control problem for discrete-time, partially observable, linear system affected by random zero mean noise and deterministic…
A Unified Single-loop Alternating Gradient Projection Algorithm for Nonconvex-Concave and Convex-Nonconcave Minimax Problems
Zi Xu, Huiling Zhang, Yang Xu +1
Much recent research effort has been directed to the development of efficient algorithms for solving minimax problems with theoretical convergence guarantees due to the relevance o…
Complexity of Stochastic Dual Dynamic Programming
Guanghui Lan
Stochastic dual dynamic programming is a cutting plane type algorithm for multi-stage stochastic optimization originated about 30 years ago. In spite of its popularity in practice,…
Efficient Algorithms for Distributionally Robust Stochastic Optimization with Discrete Scenario Support
Zhe Zhang, Shabbir Ahmed, Guanghui Lan
Recently, there has been a growing interest in distributionally robust optimization (DRO) as a principled approach to data-driven decision making. In this paper, we consider a dist…
Stochastic First-order Methods for Convex and Nonconvex Functional Constrained Optimization
Digvijay Boob, Qi Deng, Guanghui Lan
Functional constrained optimization is becoming more and more important in machine learning and operations research. Such problems have potential applications in risk-averse machin…
A unified variance-reduced accelerated gradient method for convex optimization
Guanghui Lan, Zhize Li, Yi Zhou
We propose a novel randomized incremental gradient algorithm, namely, VAriance-Reduced Accelerated Gradient (Varag), for finite-sum optimization. Equipped with a unified step-size…
Cubic Regularization with Momentum for Nonconvex Optimization
Zhe Wang, Yi Zhou, Yingbin Liang +1
Momentum is a popular technique to accelerate the convergence in practical training, and its impact on convergence guarantee has been well-studied for first-order algorithms. Howev…
Asynchronous decentralized accelerated stochastic gradient descent
Guanghui Lan, Yi Zhou
In this work, we introduce an asynchronous decentralized accelerated stochastic gradient descent type of method for decentralized stochastic optimization, considering communication…