Guanghui Lan - RankMe

120 papers A* 6A 2B 1Journal 110

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Actor-Accelerated Policy Dual Averaging for Reinforcement Learning in Continuous Action Spaces. CoRR Ji Gao, Caleb Ju, Guanghui Lan, Zhaohui Tong
2026	J	`jnl`	One-Sided Matrix Completion from Ultra-Sparse Samples. CoRR Hongyang R. Zhang, Zhenshuo Zhang, Huy L. Nguyen, Guanghui Lan
2026	J	`jnl`	One-Sided Matrix Completion from Ultra-Sparse Samples. Trans. Mach. Learn. Res. Hongyang R. Zhang, Zhenshuo Zhang, Huy L. Nguyen, Guanghui Lan
2025	J	`jnl`	A Model-Free First-Order Method for Linear Quadratic Regulator with \(\boldsymbol{\tilde {O}(1/\varepsilon )}\) Sampling Complexity. SIAM J. Control. Optim. Caleb Ju, Georgios Kotsalis, Guanghui Lan
2025	J	`jnl`	Accelerated stochastic approximation with state-dependent noise. Math. Program. Sasila Ilandarideva, Anatoli B. Juditsky, Guanghui Lan, Tianjiao Li
2025	J	`jnl`	Auto-exploration for online reinforcement learning. CoRR Caleb Ju, Guanghui Lan
2025	J	`jnl`	Can SGD Handle Heavy-Tailed Noise? CoRR Ilyas Fatkhullin, Florian Hübler, Guanghui Lan
2025	J	`jnl`	Data-Driven Minimax Optimization with Expectation Constraints. Oper. Res. Shuoguang Yang, Xudong Li, Guanghui Lan
2025	J	`jnl`	Global Solutions to Non-Convex Functional Constrained Problems with Hidden Convexity. CoRR Ilyas Fatkhullin, Niao He, Guanghui Lan, Florian Wolf
2025	J	`jnl`	Level constrained first order methods for function constrained optimization. Math. Program. Digvijay Boob, Qi Deng, Guanghui Lan
2025	J	`jnl`	Optimal methods for convex nested stochastic composite optimization. Math. Program. Zhe Zhang, Guanghui Lan
2025	J	`jnl`	Policy Mirror Descent Inherently Explores Action Space. SIAM J. Optim. Yan Li, Guanghui Lan
2025	J	`jnl`	Stochastic First-Order Methods for Average-Reward Markov Decision Processes. Math. Oper. Res. Tianjiao Li, Feiyang Wu, Guanghui Lan
2024	J	`jnl`	Auto-conditioned primal-dual hybrid gradient method and alternating direction method of multipliers. CoRR Guanghui Lan, Tianjiao Li
2024	J	`jnl`	Faster algorithm and sharper analysis for constrained Markov decision process. Oper. Res. Lett. Tianjiao Li, Ziwei Guan, Shaofeng Zou, Tengyu Xu, Yingbin Liang, Guanghui Lan
2024	J	`jnl`	Homotopic policy mirror descent: policy convergence, algorithmic regularization, and improved sample complexity. Math. Program. Yan Li, Guanghui Lan, Tuo Zhao
2024	J	`jnl`	Numerical Methods for Convex Multistage Stochastic Optimization. Found. Trends Optim. Guanghui Lan, Alexander Shapiro
2024	J	`jnl`	Projected gradient methods for nonconvex and stochastic optimization: new complexities and auto-conditioned stepsizes. CoRR Guanghui Lan, Tianjiao Li, Yangyang Xu
2024	J	`jnl`	Strongly-Polynomial Time and Validation Analysis of Policy Gradient Methods. CoRR Caleb Ju, Guanghui Lan
2023	J	`jnl`	A simple uniformly optimal method without line search for convex optimization. CoRR Tianjiao Li, Guanghui Lan
2023	J	`jnl`	A unified single-loop alternating gradient projection algorithm for nonconvex-concave and convex-nonconcave minimax problems. Math. Program. Zi Xu, Huiling Zhang, Yang Xu, Guanghui Lan
2023	J	`jnl`	Accelerated and Instance-Optimal Policy Evaluation with Linear Function Approximation. SIAM J. Math. Data Sci. Tianjiao Li, Guanghui Lan, Ashwin Pananjady
2023	J	`jnl`	Accelerated stochastic approximation with state-dependent noise. CoRR Sasila Ilandarideva, Anatoli B. Juditsky, Guanghui Lan, Tianjiao Li
2023	J	`jnl`	Block Policy Mirror Descent. SIAM J. Optim. Guanghui Lan, Yan Li, Tuo Zhao
2023	J	`jnl`	First-order Policy Optimization for Robust Policy Evaluation. CoRR Yan Li, Guanghui Lan
2023	J	`jnl`	Graph Topology Invariant Gradient and Sampling Complexity for Decentralized and Stochastic Optimization. SIAM J. Optim. Guanghui Lan, Yuyuan Ouyang, Yi Zhou
2023	J	`jnl`	Numerical Methods for Convex Multistage Stochastic Optimization. CoRR Guanghui Lan, Alexander Shapiro
2023	J	`jnl`	Optimal Methods for Convex Risk-Averse Distributed Optimization. SIAM J. Optim. Guanghui Lan, Zhe Zhang
2023	J	`jnl`	Policy Mirror Descent Inherently Explores Action Space. CoRR Yan Li, Guanghui Lan
2023	J	`jnl`	Policy mirror descent for reinforcement learning: linear convergence, new sampling complexity, and generalized problem classes. Math. Program. Guanghui Lan
2023	J	`jnl`	Stochastic first-order methods for convex and nonconvex functional constrained optimization. Math. Program. Digvijay Boob, Qi Deng, Guanghui Lan
2022	J	`jnl`	Accelerated gradient sliding for structured convex optimization. Comput. Optim. Appl. Guanghui Lan, Yuyuan Ouyang
2022	J	`jnl`	Block Policy Mirror Descent. CoRR Guanghui Lan, Yan Li, Tuo Zhao
2022	J	`jnl`	Complexity of stochastic dual dynamic programming. Math. Program. Guanghui Lan
2022	J	`jnl`	Complexity of training ReLU neural network. Discret. Optim. Digvijay Boob, Santanu S. Dey, Guanghui Lan
2022	J	`jnl`	Correction to: Complexity of stochastic dual dynamic programming. Math. Program. Guanghui Lan
2022	J	`jnl`	Data-Driven Minimax Optimization with Expectation Constraints. CoRR Shuoguang Yang, Xudong Li, Guanghui Lan
2022	J	`jnl`	First-order Policy Optimization for Robust Markov Decision Process. CoRR Yan Li, Tuo Zhao, Guanghui Lan
2022	A*	`conf`	Frequency-aware SGD for Efficient Embedding Learning with Provable Benefits. ICLR Yan Li, Dhruv Choudhary, Xiaohan Wei, Baichuan Yuan, Bhargav Bhushanam, Tuo Zhao, Guanghui Lan
2022	J	`jnl`	Functional Constrained Optimization for Risk Aversion and Sparsity Control. CoRR Yi Cheng, Guanghui Lan, H. Edwin Romeijn
2022	J	`jnl`	Homotopic Policy Mirror Descent: Policy Convergence, Implicit Regularization, and Improved Sample Complexity. CoRR Yan Li, Tuo Zhao, Guanghui Lan
2022	J	`jnl`	Optimal Methods for Risk Averse Distributed Optimization. CoRR Guanghui Lan, Zhe Zhang
2022	J	`jnl`	Policy Optimization over General State and Action Spaces. CoRR Guanghui Lan
2022	J	`jnl`	Simple and Optimal Methods for Stochastic Variational Inequalities, I: Operator Extrapolation. SIAM J. Optim. Georgios Kotsalis, Guanghui Lan, Tianjiao Li
2022	J	`jnl`	Simple and Optimal Methods for Stochastic Variational Inequalities, II: Markovian Noise and Policy Evaluation in Reinforcement Learning. SIAM J. Optim. Georgios Kotsalis, Guanghui Lan, Tianjiao Li
2022	J	`jnl`	Stochastic first-order methods for average-reward Markov decision processes. CoRR Tianjiao Li, Feiyang Wu, Guanghui Lan
2021	J	`jnl`	Accelerated and instance-optimal policy evaluation with linear function approximation. CoRR Tianjiao Li, Guanghui Lan, Ashwin Pananjady
2021	J	`jnl`	Asynchronous Decentralized Accelerated Stochastic Gradient Descent. IEEE J. Sel. Areas Inf. Theory Guanghui Lan, Yi Zhou
2021	A*	`conf`	CRPO: A New Approach for Safe Reinforcement Learning with Convergence Guarantee. ICML Tengyu Xu, Yingbin Liang, Guanghui Lan
2021	J	`jnl`	Conditional Gradient Methods for Convex Optimization with General Affine and Nonlinear Constraints. SIAM J. Optim. Guanghui Lan, H. Edwin Romeijn, Zhiqiang Zhou
2021	J	`jnl`	Convex Optimization for Finite-Horizon Robust Covariance Control of Linear Stochastic Systems. SIAM J. Control. Optim. Georgios Kotsalis, Guanghui Lan, Arkadi S. Nemirovsky
2021	J	`jnl`	Dynamic stochastic approximation for multi-stage stochastic optimization. Math. Program. Guanghui Lan, Zhiqiang Zhou
2021	J	`jnl`	Efficient Algorithms for Distributionally Robust Stochastic Optimization with Discrete Scenario Support. SIAM J. Optim. Zhe Zhang, Shabbir Ahmed, Guanghui Lan
2021	J	`jnl`	Faster Algorithm and Sharper Analysis for Constrained Markov Decision Process. CoRR Tianjiao Li, Ziwei Guan, Shaofeng Zou, Tengyu Xu, Yingbin Liang, Guanghui Lan
2021	J	`jnl`	Frequency-aware SGD for Efficient Embedding Learning with Provable Benefits. CoRR Yan Li, Dhruv Choudhary, Xiaohan Wei, Baichuan Yuan, Bhargav Bhushanam, Tuo Zhao, Guanghui Lan
2021	J	`jnl`	Policy Mirror Descent for Reinforcement Learning: Linear Convergence, New Sampling Complexity, and Generalized Problem Classes. CoRR Guanghui Lan
2020	A*	`conf`	A Feasible Level Proximal Point Method for Nonconvex Sparse Constrained Optimization. NeurIPS Digvijay Boob, Qi Deng, Guanghui Lan, Yilin Wang
2020	J	`jnl`	A Feasible Level Proximal Point Method for Nonconvex Sparse Constrained Optimization. CoRR Digvijay Boob, Qi Deng, Guanghui Lan, Yilin Wang
2020	J	`jnl`	A Primal Approach to Constrained Policy Optimization: Global Optimality and Finite-Time Analysis. CoRR Tengyu Xu, Yingbin Liang, Guanghui Lan
2020	J	`jnl`	A Unified Single-loop Alternating Gradient Projection Algorithm for Nonconvex-Concave and Convex-Nonconcave Minimax Problems. CoRR Zi Xu, Huiling Zhang, Yang Xu, Guanghui Lan
2020	J	`jnl`	Algorithms for stochastic optimization with function or expectation constraints. Comput. Optim. Appl. Guanghui Lan, Zhiqiang Zhou
2020	J	`jnl`	Communication-efficient algorithms for decentralized and stochastic optimization. Math. Program. Guanghui Lan, Soomin Lee, Yi Zhou
2020	J	`jnl`	Conditional Gradient Methods for Convex Optimization with Function Constraints. CoRR Guanghui Lan, H. Edwin Romeijn, Zhiqiang Zhou
2020	A*	`conf`	GLAD: Learning Sparse Graph Recovery. ICLR Harsh Shrivastava, Xinshi Chen, Binghong Chen, Guanghui Lan, Srinivas Aluru, Han Liu, Le Song
2020	J	`jnl`	Optimal Algorithms for Convex Nested Stochastic Composite Optimization. CoRR Zhe Zhang, Guanghui Lan
2020	J	`jnl`	Simple and optimal methods for stochastic variational inequalities, I: operator extrapolation. CoRR Georgios Kotsalis, Guanghui Lan, Tianjiao Li
2020	J	`jnl`	Simple and optimal methods for stochastic variational inequalities, II: Markovian noise and policy evaluation in reinforcement learning. CoRR Georgios Kotsalis, Guanghui Lan, Tianjiao Li
2019	J	`jnl`	A note on inexact gradient and Hessian conditions for cubic regularized Newton's method. Oper. Res. Lett. Zhe Wang, Yi Zhou, Yingbin Liang, Guanghui Lan
2019	A*	`conf`	A unified variance-reduced accelerated gradient method for convex optimization. NeurIPS Guanghui Lan, Zhize Li, Yi Zhou
2019	J	`jnl`	A unified variance-reduced accelerated gradient method for convex optimization. CoRR Guanghui Lan, Zhize Li, Yi Zhou
2019	J	`jnl`	Accelerated Stochastic Algorithms for Nonconvex Finite-Sum and Multiblock Optimization. SIAM J. Optim. Guanghui Lan, Yu Yang
2019	J	`jnl`	Complexity of Stochastic Dual Dynamic Programming. CoRR Guanghui Lan
2019	A	`conf`	Cubic Regularization with Momentum for Nonconvex Optimization. UAI Zhe Wang, Yi Zhou, Yingbin Liang, Guanghui Lan
2019	J	`jnl`	Fast bundle-level methods for unconstrained and ball-constrained convex optimization. Comput. Optim. Appl. Yunmei Chen, Guanghui Lan, Yuyuan Ouyang, Wei Zhang
2019	J	`jnl`	GLAD: Learning Sparse Graph Recovery. CoRR Harsh Shrivastava, Xinshi Chen, Binghong Chen, Guanghui Lan, Srinivas Aluru, Le Song
2019	J	`jnl`	Generalized Uniformly Optimal Methods for Nonlinear Programming. J. Sci. Comput. Saeed Ghadimi, Guanghui Lan, Hongchao Zhang
2019	J	`jnl`	Proximal Point Methods for Optimization with Nonconvex Functional Constraints. CoRR Digvijay Boob, Qi Deng, Guanghui Lan
2019	A	`conf`	Stochastic Variance-Reduced Cubic Regularization for Nonconvex Optimization. AISTATS Zhe Wang, Yi Zhou, Yingbin Liang, Guanghui Lan
2018	J	`jnl`	A Note on Inexact Condition for Cubic Regularized Newton's Method. CoRR Zhe Wang, Yi Zhou, Yingbin Liang, Guanghui Lan
2018	J	`jnl`	An optimal randomized incremental gradient method. Math. Program. Guanghui Lan, Yi Zhou
2018	J	`jnl`	Asynchronous decentralized accelerated stochastic gradient descent. CoRR Guanghui Lan, Yi Zhou
2018	J	`jnl`	Complexity of Training ReLU Neural Network. CoRR Digvijay Boob, Santanu S. Dey, Guanghui Lan
2018	J	`jnl`	Cubic Regularization with Momentum for Nonconvex Optimization. CoRR Zhe Wang, Yi Zhou, Yingbin Liang, Guanghui Lan
2018	J	`jnl`	Optimal Adaptive and Accelerated Stochastic Gradient Descent. CoRR Qi Deng, Yi Cheng, Guanghui Lan
2018	J	`jnl`	Random Gradient Extrapolation for Distributed and Stochastic Optimization. SIAM J. Optim. Guanghui Lan, Yi Zhou
2018	J	`jnl`	Sample Complexity of Stochastic Variance-Reduced Cubic Regularization for Nonconvex Optimization. CoRR Zhe Wang, Yi Zhou, Yingbin Liang, Guanghui Lan
2017	J	`jnl`	Accelerated schemes for a class of variational inequalities. Math. Program. Yunmei Chen, Guanghui Lan, Yuyuan Ouyang
2017	J	`jnl`	Communication-Efficient Algorithms for Decentralized and Stochastic Optimization. CoRR Guanghui Lan, Soomin Lee, Yi Zhou
2017	A*	`conf`	Conditional Accelerated Lazy Stochastic Gradient Descent. ICML Guanghui Lan, Sebastian Pokutta, Yi Zhou, Daniel Zink
2017	J	`jnl`	Conditional Accelerated Lazy Stochastic Gradient Descent. CoRR Guanghui Lan, Sebastian Pokutta, Yi Zhou, Daniel Zink
2017	J	`jnl`	Dynamic Stochastic Approximation for Multi-stage Stochastic Optimization. CoRR Guanghui Lan, Zhiqiang Zhou
2017	J	`jnl`	Random gradient extrapolation for distributed and stochastic optimization. CoRR Guanghui Lan, Yi Zhou
2017	J	`jnl`	Theoretical properties of the global optimizer of two layer neural network. CoRR Digvijay Boob, Guanghui Lan
2016	J	`jnl`	Accelerated gradient methods for nonconvex nonlinear and stochastic programming. Math. Program. Saeed Ghadimi, Guanghui Lan
2016	J	`jnl`	Conditional Gradient Sliding for Convex Optimization. SIAM J. Optim. Guanghui Lan, Yi Zhou
2016	J	`jnl`	Gradient sliding for composite optimization. Math. Program. Guanghui Lan
2016	J	`jnl`	Iteration-complexity of first-order augmented Lagrangian methods for convex programming. Math. Program. Guanghui Lan, Renato D. C. Monteiro
2016	J	`jnl`	Mini-batch stochastic approximation methods for nonconvex stochastic composite optimization. Math. Program. Saeed Ghadimi, Guanghui Lan, Hongchao Zhang
2015	B	`conf`	A novel method for 4D cone-beam computer-tomography reconstruction. Image Processing Hao Zhang, Justin C. Park, Yunmei Chen, Guanghui Lan, Bo Lu
2015	J	`jnl`	An Accelerated Linearized Alternating Direction Method of Multipliers. SIAM J. Imaging Sci. Yuyuan Ouyang, Yunmei Chen, Guanghui Lan, Eduardo Pasiliao Jr.
2015	J	`jnl`	An optimal randomized incremental gradient method. CoRR Guanghui Lan, Yi Zhou
2015	J	`jnl`	Bundle-level type methods uniformly optimal for smooth and nonsmooth convex optimization. Math. Program. Guanghui Lan
2015	J	`jnl`	On the convergence properties of non-Euclidean extragradient methods for variational inequalities with generalized monotone operators. Comput. Optim. Appl. Cong D. Dang, Guanghui Lan
2015	J	`jnl`	Stochastic Block Mirror Descent Methods for Nonsmooth and Stochastic Optimization. SIAM J. Optim. Cong D. Dang, Guanghui Lan
2014	J	`jnl`	A linearly convergent first-order algorithm for total variation minimisation in image processing. Int. J. Bioinform. Res. Appl. Cong D. Dang, Kaiyu Dai, Guanghui Lan
2014	J	`jnl`	Gradient Sliding for Composite Optimization. CoRR Guanghui Lan
2014	J	`jnl`	Optimal Primal-Dual Methods for a Class of Saddle Point Problems. SIAM J. Optim. Yunmei Chen, Guanghui Lan, Yuyuan Ouyang
2013	J	`jnl`	Iteration-complexity of first-order penalty methods for convex programming. Math. Program. Guanghui Lan, Renato D. C. Monteiro
2013	J	`jnl`	Optimal Stochastic Approximation Algorithms for Strongly Convex Stochastic Composite Optimization, II: Shrinking Procedures and Optimal Algorithms. SIAM J. Optim. Saeed Ghadimi, Guanghui Lan
2013	J	`jnl`	Stochastic First- and Zeroth-Order Methods for Nonconvex Stochastic Programming. SIAM J. Optim. Saeed Ghadimi, Guanghui Lan
2013	J	`jnl`	Stochastic First- and Zeroth-order Methods for Nonconvex Stochastic Programming. CoRR Saeed Ghadimi, Guanghui Lan
2012	J	`jnl`	An optimal method for stochastic composite optimization. Math. Program. Guanghui Lan
2012	J	`jnl`	Optimal Stochastic Approximation Algorithms for Strongly Convex Stochastic Composite Optimization I: A Generic Algorithmic Framework. SIAM J. Optim. Saeed Ghadimi, Guanghui Lan
2012	J	`jnl`	Validation analysis of mirror descent stochastic approximation method. Math. Program. Guanghui Lan, Arkadi Nemirovski, Alexander Shapiro
2011	J	`jnl`	Primal-dual first-order methods with Math. Program. Guanghui Lan, Zhaosong Lu, Renato D. C. Monteiro
2009	J	`jnl`	A Polynomial Predictor-Corrector Trust-Region Algorithm for Linear Programming. SIAM J. Optim. Guanghui Lan, Renato D. C. Monteiro, Takashi Tsuchiya
2009	—	`—`	Convex optimization under inexact first-order information. Guanghui Lan
2009	J	`jnl`	Robust Stochastic Approximation Approach to Stochastic Programming. SIAM J. Optim. Arkadi Nemirovski, Anatoli B. Juditsky, Guanghui Lan, Alexander Shapiro
2007	J	`jnl`	An effective and simple heuristic for the set covering problem. Eur. J. Oper. Res. Guanghui Lan, Gail W. DePuy, Gary E. Whitehouse
2006	J	`jnl`	On the effectiveness of incorporating randomness and memory into a multi-start metaheuristic with application to the Set Covering Problem. Comput. Ind. Eng. Guanghui Lan, Gail W. DePuy