default search action
Guanghui Lan
Person information
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
2020 – today
- 2024
- [j52]Guanghui Lan, Alexander Shapiro:
Numerical Methods for Convex Multistage Stochastic Optimization. Found. Trends Optim. 6(2): 63-144 (2024) - [j51]Yan Li, Guanghui Lan, Tuo Zhao:
Homotopic policy mirror descent: policy convergence, algorithmic regularization, and improved sample complexity. Math. Program. 207(1): 457-513 (2024) - [j50]Tianjiao Li, Ziwei Guan, Shaofeng Zou, Tengyu Xu, Yingbin Liang, Guanghui Lan:
Faster algorithm and sharper analysis for constrained Markov decision process. Oper. Res. Lett. 54: 107107 (2024) - [i44]Caleb Ju, Guanghui Lan:
Strongly-Polynomial Time and Validation Analysis of Policy Gradient Methods. CoRR abs/2409.19437 (2024) - [i43]Guanghui Lan, Tianjiao Li:
Auto-conditioned primal-dual hybrid gradient method and alternating direction method of multipliers. CoRR abs/2410.01979 (2024) - 2023
- [j49]Digvijay Boob, Qi Deng, Guanghui Lan:
Stochastic first-order methods for convex and nonconvex functional constrained optimization. Math. Program. 197(1): 215-279 (2023) - [j48]Guanghui Lan:
Policy mirror descent for reinforcement learning: linear convergence, new sampling complexity, and generalized problem classes. Math. Program. 198(1): 1059-1106 (2023) - [j47]Zi Xu, Huiling Zhang, Yang Xu, Guanghui Lan:
A unified single-loop alternating gradient projection algorithm for nonconvex-concave and convex-nonconcave minimax problems. Math. Program. 201(1): 635-706 (2023) - [j46]Guanghui Lan, Zhe Zhang:
Optimal Methods for Convex Risk-Averse Distributed Optimization. SIAM J. Optim. 33(3): 1518-1557 (2023) - [j45]Guanghui Lan, Yuyuan Ouyang, Yi Zhou:
Graph Topology Invariant Gradient and Sampling Complexity for Decentralized and Stochastic Optimization. SIAM J. Optim. 33(3): 1647-1675 (2023) - [j44]Guanghui Lan, Yan Li, Tuo Zhao:
Block Policy Mirror Descent. SIAM J. Optim. 33(3): 2341-2378 (2023) - [j43]Tianjiao Li, Guanghui Lan, Ashwin Pananjady:
Accelerated and Instance-Optimal Policy Evaluation with Linear Function Approximation. SIAM J. Math. Data Sci. 5(1): 174-200 (2023) - [i42]Yan Li, Guanghui Lan:
Policy Mirror Descent Inherently Explores Action Space. CoRR abs/2303.04386 (2023) - [i41]Guanghui Lan, Alexander Shapiro:
Numerical Methods for Convex Multistage Stochastic Optimization. CoRR abs/2303.15672 (2023) - [i40]Sasila Ilandarideva, Anatoli B. Juditsky, Guanghui Lan, Tianjiao Li:
Accelerated stochastic approximation with state-dependent noise. CoRR abs/2307.01497 (2023) - [i39]Yan Li, Guanghui Lan:
First-order Policy Optimization for Robust Policy Evaluation. CoRR abs/2307.15890 (2023) - [i38]Tianjiao Li, Guanghui Lan:
A simple uniformly optimal method without line search for convex optimization. CoRR abs/2310.10082 (2023) - 2022
- [j42]Guanghui Lan, Yuyuan Ouyang:
Accelerated gradient sliding for structured convex optimization. Comput. Optim. Appl. 82(2): 361-394 (2022) - [j41]Digvijay Boob, Santanu S. Dey, Guanghui Lan:
Complexity of training ReLU neural network. Discret. Optim. 44(Part): 100620 (2022) - [j40]Guanghui Lan:
Complexity of stochastic dual dynamic programming. Math. Program. 191(2): 717-754 (2022) - [j39]Guanghui Lan:
Correction to: Complexity of stochastic dual dynamic programming. Math. Program. 194(1): 1187-1189 (2022) - [j38]Georgios Kotsalis, Guanghui Lan, Tianjiao Li:
Simple and Optimal Methods for Stochastic Variational Inequalities, II: Markovian Noise and Policy Evaluation in Reinforcement Learning. SIAM J. Optim. 32(2): 1120-1155 (2022) - [j37]Georgios Kotsalis, Guanghui Lan, Tianjiao Li:
Simple and Optimal Methods for Stochastic Variational Inequalities, I: Operator Extrapolation. SIAM J. Optim. 32(3): 2041-2073 (2022) - [c9]Yan Li, Dhruv Choudhary, Xiaohan Wei, Baichuan Yuan, Bhargav Bhushanam, Tuo Zhao, Guanghui Lan:
Frequency-aware SGD for Efficient Embedding Learning with Provable Benefits. ICLR 2022 - [i37]Guanghui Lan, Yan Li, Tuo Zhao:
Block Policy Mirror Descent. CoRR abs/2201.05756 (2022) - [i36]Yan Li, Tuo Zhao, Guanghui Lan:
Homotopic Policy Mirror Descent: Policy Convergence, Implicit Regularization, and Improved Sample Complexity. CoRR abs/2201.09457 (2022) - [i35]Shuoguang Yang, Xudong Li, Guanghui Lan:
Data-Driven Minimax Optimization with Expectation Constraints. CoRR abs/2202.07868 (2022) - [i34]Guanghui Lan, Zhe Zhang:
Optimal Methods for Risk Averse Distributed Optimization. CoRR abs/2203.05117 (2022) - [i33]Tianjiao Li, Feiyang Wu, Guanghui Lan:
Stochastic first-order methods for average-reward Markov decision processes. CoRR abs/2205.05800 (2022) - [i32]Yan Li, Tuo Zhao, Guanghui Lan:
First-order Policy Optimization for Robust Markov Decision Process. CoRR abs/2209.10579 (2022) - [i31]Yi Cheng, Guanghui Lan, H. Edwin Romeijn:
Functional Constrained Optimization for Risk Aversion and Sparsity Control. CoRR abs/2210.05108 (2022) - [i30]Guanghui Lan:
Policy Optimization over General State and Action Spaces. CoRR abs/2211.16715 (2022) - 2021
- [j36]Guanghui Lan, Yi Zhou:
Asynchronous Decentralized Accelerated Stochastic Gradient Descent. IEEE J. Sel. Areas Inf. Theory 2(2): 802-811 (2021) - [j35]Guanghui Lan, Zhiqiang Zhou:
Dynamic stochastic approximation for multi-stage stochastic optimization. Math. Program. 187(1): 487-532 (2021) - [j34]Georgios Kotsalis, Guanghui Lan, Arkadi S. Nemirovsky:
Convex Optimization for Finite-Horizon Robust Covariance Control of Linear Stochastic Systems. SIAM J. Control. Optim. 59(1): 296-319 (2021) - [j33]Zhe Zhang, Shabbir Ahmed, Guanghui Lan:
Efficient Algorithms for Distributionally Robust Stochastic Optimization with Discrete Scenario Support. SIAM J. Optim. 31(3): 1690-1721 (2021) - [j32]Guanghui Lan, H. Edwin Romeijn, Zhiqiang Zhou:
Conditional Gradient Methods for Convex Optimization with General Affine and Nonlinear Constraints. SIAM J. Optim. 31(3): 2307-2339 (2021) - [c8]Tengyu Xu, Yingbin Liang, Guanghui Lan:
CRPO: A New Approach for Safe Reinforcement Learning with Convergence Guarantee. ICML 2021: 11480-11491 - [i29]Guanghui Lan:
Policy Mirror Descent for Reinforcement Learning: Linear Convergence, New Sampling Complexity, and Generalized Problem Classes. CoRR abs/2102.00135 (2021) - [i28]Yan Li, Dhruv Choudhary, Xiaohan Wei, Baichuan Yuan, Bhargav Bhushanam, Tuo Zhao, Guanghui Lan:
Frequency-aware SGD for Efficient Embedding Learning with Provable Benefits. CoRR abs/2110.04844 (2021) - [i27]Tianjiao Li, Ziwei Guan, Shaofeng Zou, Tengyu Xu, Yingbin Liang, Guanghui Lan:
Faster Algorithm and Sharper Analysis for Constrained Markov Decision Process. CoRR abs/2110.10351 (2021) - [i26]Tianjiao Li, Guanghui Lan, Ashwin Pananjady:
Accelerated and instance-optimal policy evaluation with linear function approximation. CoRR abs/2112.13109 (2021) - 2020
- [j31]Guanghui Lan, Zhiqiang Zhou:
Algorithms for stochastic optimization with function or expectation constraints. Comput. Optim. Appl. 76(2): 461-498 (2020) - [j30]Guanghui Lan, Soomin Lee, Yi Zhou:
Communication-efficient algorithms for decentralized and stochastic optimization. Math. Program. 180(1): 237-284 (2020) - [c7]Harsh Shrivastava, Xinshi Chen, Binghong Chen, Guanghui Lan, Srinivas Aluru, Han Liu, Le Song:
GLAD: Learning Sparse Graph Recovery. ICLR 2020 - [c6]Digvijay Boob, Qi Deng, Guanghui Lan, Yilin Wang:
A Feasible Level Proximal Point Method for Nonconvex Sparse Constrained Optimization. NeurIPS 2020 - [i25]Zi Xu, Huiling Zhang, Yang Xu, Guanghui Lan:
A Unified Single-loop Alternating Gradient Projection Algorithm for Nonconvex-Concave and Convex-Nonconcave Minimax Problems. CoRR abs/2006.02032 (2020) - [i24]Guanghui Lan, H. Edwin Romeijn, Zhiqiang Zhou:
Conditional Gradient Methods for Convex Optimization with Function Constraints. CoRR abs/2007.00153 (2020) - [i23]Digvijay Boob, Qi Deng, Guanghui Lan, Yilin Wang:
A Feasible Level Proximal Point Method for Nonconvex Sparse Constrained Optimization. CoRR abs/2010.12169 (2020) - [i22]Georgios Kotsalis, Guanghui Lan, Tianjiao Li:
Simple and optimal methods for stochastic variational inequalities, I: operator extrapolation. CoRR abs/2011.02987 (2020) - [i21]Tengyu Xu, Yingbin Liang, Guanghui Lan:
A Primal Approach to Constrained Policy Optimization: Global Optimality and Finite-Time Analysis. CoRR abs/2011.05869 (2020) - [i20]Georgios Kotsalis, Guanghui Lan, Tianjiao Li:
Simple and optimal methods for stochastic variational inequalities, II: Markovian noise and policy evaluation in reinforcement learning. CoRR abs/2011.08434 (2020) - [i19]Zhe Zhang, Guanghui Lan:
Optimal Algorithms for Convex Nested Stochastic Composite Optimization. CoRR abs/2011.10076 (2020)
2010 – 2019
- 2019
- [j29]Yunmei Chen, Guanghui Lan, Yuyuan Ouyang, Wei Zhang:
Fast bundle-level methods for unconstrained and ball-constrained convex optimization. Comput. Optim. Appl. 73(1): 159-199 (2019) - [j28]Saeed Ghadimi, Guanghui Lan, Hongchao Zhang:
Generalized Uniformly Optimal Methods for Nonlinear Programming. J. Sci. Comput. 79(3): 1854-1881 (2019) - [j27]Zhe Wang, Yi Zhou, Yingbin Liang, Guanghui Lan:
A note on inexact gradient and Hessian conditions for cubic regularized Newton's method. Oper. Res. Lett. 47(2): 146-149 (2019) - [j26]Guanghui Lan, Yu Yang:
Accelerated Stochastic Algorithms for Nonconvex Finite-Sum and Multiblock Optimization. SIAM J. Optim. 29(4): 2753-2784 (2019) - [c5]Zhe Wang, Yi Zhou, Yingbin Liang, Guanghui Lan:
Stochastic Variance-Reduced Cubic Regularization for Nonconvex Optimization. AISTATS 2019: 2731-2740 - [c4]Guanghui Lan, Zhize Li, Yi Zhou:
A unified variance-reduced accelerated gradient method for convex optimization. NeurIPS 2019: 10462-10472 - [c3]Zhe Wang, Yi Zhou, Yingbin Liang, Guanghui Lan:
Cubic Regularization with Momentum for Nonconvex Optimization. UAI 2019: 313-322 - [i18]Guanghui Lan, Zhize Li, Yi Zhou:
A unified variance-reduced accelerated gradient method for convex optimization. CoRR abs/1905.12412 (2019) - [i17]Harsh Shrivastava, Xinshi Chen, Binghong Chen, Guanghui Lan, Srinivas Aluru, Le Song:
GLAD: Learning Sparse Graph Recovery. CoRR abs/1906.00271 (2019) - [i16]Digvijay Boob, Qi Deng, Guanghui Lan:
Proximal Point Methods for Optimization with Nonconvex Functional Constraints. CoRR abs/1908.02734 (2019) - [i15]Guanghui Lan:
Complexity of Stochastic Dual Dynamic Programming. CoRR abs/1912.07702 (2019) - 2018
- [j25]Guanghui Lan, Yi Zhou:
An optimal randomized incremental gradient method. Math. Program. 171(1-2): 167-215 (2018) - [j24]Guanghui Lan, Yi Zhou:
Random Gradient Extrapolation for Distributed and Stochastic Optimization. SIAM J. Optim. 28(4): 2753-2782 (2018) - [i14]Zhe Wang, Yi Zhou, Yingbin Liang, Guanghui Lan:
Sample Complexity of Stochastic Variance-Reduced Cubic Regularization for Nonconvex Optimization. CoRR abs/1802.07372 (2018) - [i13]Zhe Wang, Yi Zhou, Yingbin Liang, Guanghui Lan:
A Note on Inexact Condition for Cubic Regularized Newton's Method. CoRR abs/1808.07384 (2018) - [i12]Guanghui Lan, Yi Zhou:
Asynchronous decentralized accelerated stochastic gradient descent. CoRR abs/1809.09258 (2018) - [i11]Digvijay Boob, Santanu S. Dey, Guanghui Lan:
Complexity of Training ReLU Neural Network. CoRR abs/1809.10787 (2018) - [i10]Qi Deng, Yi Cheng, Guanghui Lan:
Optimal Adaptive and Accelerated Stochastic Gradient Descent. CoRR abs/1810.00553 (2018) - [i9]Zhe Wang, Yi Zhou, Yingbin Liang, Guanghui Lan:
Cubic Regularization with Momentum for Nonconvex Optimization. CoRR abs/1810.03763 (2018) - 2017
- [j23]Yunmei Chen, Guanghui Lan, Yuyuan Ouyang:
Accelerated schemes for a class of variational inequalities. Math. Program. 165(1): 113-149 (2017) - [c2]Guanghui Lan, Sebastian Pokutta, Yi Zhou, Daniel Zink:
Conditional Accelerated Lazy Stochastic Gradient Descent. ICML 2017: 1965-1974 - [i8]Guanghui Lan, Soomin Lee, Yi Zhou:
Communication-Efficient Algorithms for Decentralized and Stochastic Optimization. CoRR abs/1701.03961 (2017) - [i7]Guanghui Lan, Sebastian Pokutta, Yi Zhou, Daniel Zink:
Conditional Accelerated Lazy Stochastic Gradient Descent. CoRR abs/1703.05840 (2017) - [i6]Guanghui Lan, Zhiqiang Zhou:
Dynamic Stochastic Approximation for Multi-stage Stochastic Optimization. CoRR abs/1707.03324 (2017) - [i5]Digvijay Boob, Guanghui Lan:
Theoretical properties of the global optimizer of two layer neural network. CoRR abs/1710.11241 (2017) - [i4]Guanghui Lan, Yi Zhou:
Random gradient extrapolation for distributed and stochastic optimization. CoRR abs/1711.05762 (2017) - 2016
- [j22]Saeed Ghadimi, Guanghui Lan, Hongchao Zhang:
Mini-batch stochastic approximation methods for nonconvex stochastic composite optimization. Math. Program. 155(1-2): 267-305 (2016) - [j21]Guanghui Lan, Renato D. C. Monteiro:
Iteration-complexity of first-order augmented Lagrangian methods for convex programming. Math. Program. 155(1-2): 511-547 (2016) - [j20]Saeed Ghadimi, Guanghui Lan:
Accelerated gradient methods for nonconvex nonlinear and stochastic programming. Math. Program. 156(1-2): 59-99 (2016) - [j19]Guanghui Lan:
Gradient sliding for composite optimization. Math. Program. 159(1-2): 201-235 (2016) - [j18]Guanghui Lan, Yi Zhou:
Conditional Gradient Sliding for Convex Optimization. SIAM J. Optim. 26(2): 1379-1409 (2016) - 2015
- [j17]Cong D. Dang, Guanghui Lan:
On the convergence properties of non-Euclidean extragradient methods for variational inequalities with generalized monotone operators. Comput. Optim. Appl. 60(2): 277-310 (2015) - [j16]Guanghui Lan:
Bundle-level type methods uniformly optimal for smooth and nonsmooth convex optimization. Math. Program. 149(1-2): 1-45 (2015) - [j15]Yuyuan Ouyang, Yunmei Chen, Guanghui Lan, Eduardo Pasiliao Jr.:
An Accelerated Linearized Alternating Direction Method of Multipliers. SIAM J. Imaging Sci. 8(1): 644-681 (2015) - [j14]Cong D. Dang, Guanghui Lan:
Stochastic Block Mirror Descent Methods for Nonsmooth and Stochastic Optimization. SIAM J. Optim. 25(2): 856-881 (2015) - [c1]Hao Zhang, Justin C. Park, Yunmei Chen, Guanghui Lan, Bo Lu:
A novel method for 4D cone-beam computer-tomography reconstruction. Image Processing 2015: 941324 - [i3]Guanghui Lan, Yi Zhou:
An optimal randomized incremental gradient method. CoRR abs/1507.02000 (2015) - 2014
- [j13]Cong D. Dang, Kaiyu Dai, Guanghui Lan:
A linearly convergent first-order algorithm for total variation minimisation in image processing. Int. J. Bioinform. Res. Appl. 10(1): 4-26 (2014) - [j12]Yunmei Chen, Guanghui Lan, Yuyuan Ouyang:
Optimal Primal-Dual Methods for a Class of Saddle Point Problems. SIAM J. Optim. 24(4): 1779-1814 (2014) - [i2]Guanghui Lan:
Gradient Sliding for Composite Optimization. CoRR abs/1406.0919 (2014) - 2013
- [j11]Guanghui Lan, Renato D. C. Monteiro:
Iteration-complexity of first-order penalty methods for convex programming. Math. Program. 138(1-2): 115-139 (2013) - [j10]Saeed Ghadimi, Guanghui Lan:
Optimal Stochastic Approximation Algorithms for Strongly Convex Stochastic Composite Optimization, II: Shrinking Procedures and Optimal Algorithms. SIAM J. Optim. 23(4): 2061-2089 (2013) - [j9]Saeed Ghadimi, Guanghui Lan:
Stochastic First- and Zeroth-Order Methods for Nonconvex Stochastic Programming. SIAM J. Optim. 23(4): 2341-2368 (2013) - [i1]Saeed Ghadimi, Guanghui Lan:
Stochastic First- and Zeroth-order Methods for Nonconvex Stochastic Programming. CoRR abs/1309.5549 (2013) - 2012
- [j8]Guanghui Lan:
An optimal method for stochastic composite optimization. Math. Program. 133(1-2): 365-397 (2012) - [j7]Guanghui Lan, Arkadi Nemirovski, Alexander Shapiro:
Validation analysis of mirror descent stochastic approximation method. Math. Program. 134(2): 425-458 (2012) - [j6]Saeed Ghadimi, Guanghui Lan:
Optimal Stochastic Approximation Algorithms for Strongly Convex Stochastic Composite Optimization I: A Generic Algorithmic Framework. SIAM J. Optim. 22(4): 1469-1492 (2012) - 2011
- [j5]Guanghui Lan, Zhaosong Lu, Renato D. C. Monteiro:
Primal-dual first-order methods with O(1/e) iteration-complexity for cone programming. Math. Program. 126(1): 1-29 (2011)
2000 – 2009
- 2009
- [j4]Arkadi Nemirovski, Anatoli B. Juditsky, Guanghui Lan, Alexander Shapiro:
Robust Stochastic Approximation Approach to Stochastic Programming. SIAM J. Optim. 19(4): 1574-1609 (2009) - [j3]Guanghui Lan, Renato D. C. Monteiro, Takashi Tsuchiya:
A Polynomial Predictor-Corrector Trust-Region Algorithm for Linear Programming. SIAM J. Optim. 19(4): 1918-1946 (2009) - 2007
- [j2]Guanghui Lan, Gail W. DePuy, Gary E. Whitehouse:
An effective and simple heuristic for the set covering problem. Eur. J. Oper. Res. 176(3): 1387-1403 (2007) - 2006
- [j1]Guanghui Lan, Gail W. DePuy:
On the effectiveness of incorporating randomness and memory into a multi-start metaheuristic with application to the Set Covering Problem. Comput. Ind. Eng. 51(3): 362-374 (2006)
Coauthor Index
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from , , and to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from .
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2024-12-01 00:13 CET by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint