Guanghui Lan

Math. Program., January, 2025

2024

Homotopic policy mirror descent: policy convergence, algorithmic regularization, and improved sample complexity.

[BibT_eX]

[DOI]

Math. Program., September, 2024

Faster algorithm and sharper analysis for constrained Markov decision process.

[BibT_eX]

[DOI]

Oper. Res. Lett., 2024

Numerical Methods for Convex Multistage Stochastic Optimization.

[BibT_eX]

[DOI]

Alexander Shapiro

Found. Trends Optim., 2024

Projected gradient methods for nonconvex and stochastic optimization: new complexities and auto-conditioned stepsizes.

[BibT_eX]

[DOI]

Yangyang Xu

CoRR, 2024

Auto-conditioned primal-dual hybrid gradient method and alternating direction method of multipliers.

[BibT_eX]

[DOI]

CoRR, 2024

Strongly-Polynomial Time and Validation Analysis of Policy Gradient Methods.

[BibT_eX]

[DOI]

Caleb Ju

CoRR, 2024

2023

Optimal Methods for Convex Risk-Averse Distributed Optimization.

[BibT_eX]

[DOI]

SIAM J. Optim., September, 2023

Graph Topology Invariant Gradient and Sampling Complexity for Decentralized and Stochastic Optimization.

[BibT_eX]

[DOI]

SIAM J. Optim., September, 2023

Block Policy Mirror Descent.

[BibT_eX]

[DOI]

SIAM J. Optim., September, 2023

Accelerated and Instance-Optimal Policy Evaluation with Linear Function Approximation.

[BibT_eX]

[DOI]

Ashwin Pananjady

SIAM J. Math. Data Sci., March, 2023

Policy mirror descent for reinforcement learning: linear convergence, new sampling complexity, and generalized problem classes.

[BibT_eX]

[DOI]

Math. Program., March, 2023

Stochastic first-order methods for convex and nonconvex functional constrained optimization.

[BibT_eX]

[DOI]

Math. Program., January, 2023

A unified single-loop alternating gradient projection algorithm for nonconvex-concave and convex-nonconcave minimax problems.

[BibT_eX]

[DOI]

Math. Program., 2023

A simple uniformly optimal method without line search for convex optimization.

[BibT_eX]

[DOI]

CoRR, 2023

First-order Policy Optimization for Robust Policy Evaluation.

[BibT_eX]

[DOI]

CoRR, 2023

Accelerated stochastic approximation with state-dependent noise.

[BibT_eX]

[DOI]

CoRR, 2023

Policy Mirror Descent Inherently Explores Action Space.

[BibT_eX]

[DOI]

CoRR, 2023

2022

Simple and Optimal Methods for Stochastic Variational Inequalities, I: Operator Extrapolation.

[BibT_eX]

[DOI]

Georgios Kotsalis

SIAM J. Optim., September, 2022

Simple and Optimal Methods for Stochastic Variational Inequalities, II: Markovian Noise and Policy Evaluation in Reinforcement Learning.

[BibT_eX]

[DOI]

Georgios Kotsalis

SIAM J. Optim., 2022

Correction to: Complexity of stochastic dual dynamic programming.

[BibT_eX]

[DOI]

Math. Program., 2022

Complexity of stochastic dual dynamic programming.

[BibT_eX]

[DOI]

Math. Program., 2022

Complexity of training ReLU neural network.

[BibT_eX]

[DOI]

Santanu S. Dey

Discret. Optim., 2022

Policy Optimization over General State and Action Spaces.

[BibT_eX]

[DOI]

CoRR, 2022

Functional Constrained Optimization for Risk Aversion and Sparsity Control.

[BibT_eX]

[DOI]

Yi Cheng

H. Edwin Romeijn

CoRR, 2022

First-order Policy Optimization for Robust Markov Decision Process.

[BibT_eX]

[DOI]

CoRR, 2022

Stochastic first-order methods for average-reward Markov decision processes.

[BibT_eX]

[DOI]

Feiyang Wu

CoRR, 2022

Optimal Methods for Risk Averse Distributed Optimization.

[BibT_eX]

[DOI]

CoRR, 2022

Data-Driven Minimax Optimization with Expectation Constraints.

[BibT_eX]

[DOI]

Shuoguang Yang

Xudong Li

CoRR, 2022

Homotopic Policy Mirror Descent: Policy Convergence, Implicit Regularization, and Improved Sample Complexity.

[BibT_eX]

[DOI]

CoRR, 2022

Accelerated gradient sliding for structured convex optimization.

[BibT_eX]

[DOI]

Comput. Optim. Appl., 2022

Frequency-aware SGD for Efficient Embedding Learning with Provable Benefits.

[BibT_eX]

[DOI]

Proceedings of the Tenth International Conference on Learning Representations, 2022

2021

Efficient Algorithms for Distributionally Robust Stochastic Optimization with Discrete Scenario Support.

[BibT_eX]

[DOI]

Shabbir Ahmed

SIAM J. Optim., 2021

Conditional Gradient Methods for Convex Optimization with General Affine and Nonlinear Constraints.

[BibT_eX]

[DOI]

H. Edwin Romeijn

SIAM J. Optim., 2021

Convex Optimization for Finite-Horizon Robust Covariance Control of Linear Stochastic Systems.

[BibT_eX]

[DOI]

Georgios Kotsalis

Arkadi S. Nemirovsky

SIAM J. Control. Optim., 2021

Dynamic stochastic approximation for multi-stage stochastic optimization.

[BibT_eX]

[DOI]

Math. Program., 2021

Asynchronous Decentralized Accelerated Stochastic Gradient Descent.

[BibT_eX]

[DOI]

IEEE J. Sel. Areas Inf. Theory, 2021

CRPO: A New Approach for Safe Reinforcement Learning with Convergence Guarantee.

[BibT_eX]

[DOI]

Tengyu Xu

Yingbin Liang

Proceedings of the 38th International Conference on Machine Learning, 2021

2020

Communication-efficient algorithms for decentralized and stochastic optimization.

[BibT_eX]

[DOI]

Soomin Lee

Math. Program., 2020

Optimal Algorithms for Convex Nested Stochastic Composite Optimization.

[BibT_eX]

[DOI]

CoRR, 2020

A Primal Approach to Constrained Policy Optimization: Global Optimality and Finite-Time Analysis.

[BibT_eX]

[DOI]

Tengyu Xu

Yingbin Liang

CoRR, 2020

Conditional Gradient Methods for Convex Optimization with Function Constraints.

[BibT_eX]

[DOI]

H. Edwin Romeijn

CoRR, 2020

Algorithms for stochastic optimization with function or expectation constraints.

[BibT_eX]

[DOI]

Comput. Optim. Appl., 2020

A Feasible Level Proximal Point Method for Nonconvex Sparse Constrained Optimization.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

GLAD: Learning Sparse Graph Recovery.

[BibT_eX]

[DOI]

Proceedings of the 8th International Conference on Learning Representations, 2020

2019

Accelerated Stochastic Algorithms for Nonconvex Finite-Sum and Multiblock Optimization.

[BibT_eX]

[DOI]

Yu Yang

SIAM J. Optim., 2019

A note on inexact gradient and Hessian conditions for cubic regularized Newton's method.

[BibT_eX]

[DOI]

Oper. Res. Lett., 2019

Generalized Uniformly Optimal Methods for Nonlinear Programming.

[BibT_eX]

[DOI]

Hongchao Zhang

J. Sci. Comput., 2019

Proximal Point Methods for Optimization with Nonconvex Functional Constraints.

[BibT_eX]

[DOI]

CoRR, 2019

GLAD: Learning Sparse Graph Recovery.

[BibT_eX]

[DOI]

CoRR, 2019

Fast bundle-level methods for unconstrained and ball-constrained convex optimization.

[BibT_eX]

[DOI]

Comput. Optim. Appl., 2019

Cubic Regularization with Momentum for Nonconvex Optimization.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Fifth Conference on Uncertainty in Artificial Intelligence, 2019

A unified variance-reduced accelerated gradient method for convex optimization.

[BibT_eX]

[DOI]

Zhize Li

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Stochastic Variance-Reduced Cubic Regularization for Nonconvex Optimization.

[BibT_eX]

[DOI]

Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics, 2019

2018

Random Gradient Extrapolation for Distributed and Stochastic Optimization.

[BibT_eX]

[DOI]

SIAM J. Optim., 2018

An optimal randomized incremental gradient method.

[BibT_eX]

[DOI]

Math. Program., 2018

Optimal Adaptive and Accelerated Stochastic Gradient Descent.

[BibT_eX]

[DOI]

Yi Cheng

CoRR, 2018

A Note on Inexact Condition for Cubic Regularized Newton's Method.

[BibT_eX]

[DOI]

CoRR, 2018

Sample Complexity of Stochastic Variance-Reduced Cubic Regularization for Nonconvex Optimization.

[BibT_eX]

[DOI]

CoRR, 2018

2017

Accelerated schemes for a class of variational inequalities.

[BibT_eX]

[DOI]

Yunmei Chen

Math. Program., 2017

Theoretical properties of the global optimizer of two layer neural network.

[BibT_eX]

[DOI]

CoRR, 2017

Conditional Accelerated Lazy Stochastic Gradient Descent.

[BibT_eX]

[DOI]

Proceedings of the 34th International Conference on Machine Learning, 2017

2016

Conditional Gradient Sliding for Convex Optimization.

[BibT_eX]

SIAM J. Optim., 2016

Iteration-complexity of first-order augmented Lagrangian methods for convex programming.

[BibT_eX]

[DOI]

Math. Program., 2016

Gradient sliding for composite optimization.

[BibT_eX]

[DOI]

Math. Program., 2016

Mini-batch stochastic approximation methods for nonconvex stochastic composite optimization.

[BibT_eX]

[DOI]

Hongchao Zhang

Math. Program., 2016

Accelerated gradient methods for nonconvex nonlinear and stochastic programming.

[BibT_eX]

[DOI]

Math. Program., 2016

2015

Stochastic Block Mirror Descent Methods for Nonsmooth and Stochastic Optimization.

[BibT_eX]

[DOI]

Cong D. Dang

SIAM J. Optim., 2015

An Accelerated Linearized Alternating Direction Method of Multipliers.

[BibT_eX]

[DOI]

SIAM J. Imaging Sci., 2015

Bundle-level type methods uniformly optimal for smooth and nonsmooth convex optimization.

[BibT_eX]

[DOI]

Math. Program., 2015

On the convergence properties of non-Euclidean extragradient methods for variational inequalities with generalized monotone operators.

[BibT_eX]

[DOI]

Cong D. Dang

Comput. Optim. Appl., 2015

A novel method for 4D cone-beam computer-tomography reconstruction.

[BibT_eX]

[DOI]

Proceedings of the Medical Imaging 2015: Image Processing, 2015

2014

Optimal Primal-Dual Methods for a Class of Saddle Point Problems.

[BibT_eX]

[DOI]

Yunmei Chen

SIAM J. Optim., 2014

A linearly convergent first-order algorithm for total variation minimisation in image processing.

[BibT_eX]

[DOI]

Cong D. Dang

Kaiyu Dai

Int. J. Bioinform. Res. Appl., 2014

2013

Stochastic First- and Zeroth-Order Methods for Nonconvex Stochastic Programming.

[BibT_eX]

[DOI]

SIAM J. Optim., 2013

Optimal Stochastic Approximation Algorithms for Strongly Convex Stochastic Composite Optimization, II: Shrinking Procedures and Optimal Algorithms.

[BibT_eX]

[DOI]

SIAM J. Optim., 2013

Iteration-complexity of first-order penalty methods for convex programming.

[BibT_eX]

[DOI]

Math. Program., 2013

2012

Optimal Stochastic Approximation Algorithms for Strongly Convex Stochastic Composite Optimization I: A Generic Algorithmic Framework.

[BibT_eX]

[DOI]

SIAM J. Optim., 2012

Validation analysis of mirror descent stochastic approximation method.

[BibT_eX]

[DOI]

Arkadi Nemirovski

Alexander Shapiro

Math. Program., 2012

An optimal method for stochastic composite optimization.

[BibT_eX]

[DOI]

Math. Program., 2012

2011

Primal-dual first-order methods with <i>O</i>(1/e) iteration-complexity for cone programming.

[BibT_eX]

[DOI]

Zhaosong Lu

Math. Program., 2011

2009

Robust Stochastic Approximation Approach to Stochastic Programming.

[BibT_eX]

[DOI]

SIAM J. Optim., 2009

A Polynomial Predictor-Corrector Trust-Region Algorithm for Linear Programming.

[BibT_eX]

[DOI]

Takashi Tsuchiya

SIAM J. Optim., 2009

2007

An effective and simple heuristic for the set covering problem.

[BibT_eX]

[DOI]

Gail W. DePuy

Gary E. Whitehouse

Eur. J. Oper. Res., 2007

2006

On the effectiveness of incorporating randomness and memory into a multi-start metaheuristic with application to the Set Covering Problem.

[BibT_eX]

[DOI]