Lin Xiao – Papers

Google scholar page

2025

• Smoothing DiLoCo with Primal Averaging for Faster Training of LLMs
  Aaron Defazio, Konstantin Mishchenko, Parameswaran Raman, Hao-Jun Michael Shi, Lin Xiao
  arXiv preprint, 2025.

• Stochastic Approximation with Block Coordinate Optimal Stepsizes
  Tao Jiang and Lin Xiao
  arXiv preprint, 2025.

• Quantization through Piecewise-Affine Regularization: Optimization and Statistical Guarantees
  Jianhao Ma and Lin Xiao
  arXiv preprint, 2025.

• Exploration from a Primal-Dual Lens: Value-Incentivized Actor-Critic Methods for Sample-Efficient Online RL
  Tong Yang, Bo Dai, Lin Xiao, Yuejie Chi
  NeurIPS 2025.

• ParetoQ: Improving Scaling Laws in Extremely Low-bit LLM Quantization
  Zechun Liu, Changsheng Zhao, Hanxian Huang, Sijia Chen, Jing Zhang, Jiawei Zhao, Scott Roy, Lisa Jin, Yunyang Xiong, Yangyang Shi, Lin Xiao, Yuandong Tian, Bilge Soran, Raghuraman Krishnamoorthi, Tijmen Blankevoort, Vikas Chandra
  NeurIPS 2025.

• LoRe: Personalizing LLMs via Low-Rank Reward Modeling
  Avinandan Bose, Zhihan Xiong, Yuejie Chi, Simon Shaolei Du, Lin Xiao, Maryam Fazel
  Proceedings of Second Conference on Language Modeling (CoLM), 2025.

• PARQ: Piecewise-Affine Regularized Quantization
  Lisa Jin, Jianhao Ma, Zechun Liu, Andrey Gromov, Aaron Defazio, Lin Xiao
  ICML 2025.

• Incentivize without Bonus: Provably Efficient Model-based Online Multi-agent RL for Markov Games
  Tong Yang, Bo Dai, Lin Xiao, Yuejie Chi
  ICML 2025.

2024

• Noisy recovery from random linear observations: Sharp minimax rates under elliptical constraints
  Reese Pathak, Martin J. Wainwright, Lin Xiao
  The Annals of Statistics, 52(6):2816-2850, December 2024.

• Dual Approximation Policy Optimization
  Zhihan Xiong, Maryam Fazel and Lin Xiao
  arXiv preprint, 2024.

• An Adaptive Stochastic Gradient Method with Non-negative Gauss-Newton Stepsizes
  Antonio Orvieto and Lin Xiao
  arXiv preprint, 2024.

2023

• Linear Convergence of Natural Policy Gradient Methods with Log-Linear Policies
  Rui Yuan, Simon Shaolei Du, Robert M. Gower, Alessandro Lazaric, Lin Xiao
  ICLR 2023.

• Faster Last-iterate Convergence of Policy Optimization in Zero-Sum Markov Games
  Shicong Cen, Yuejie Chi, Simon S. Du, Lin Xiao
  ICLR 2023.

2022

• Stochastic Optimization with Decision-Dependent Distributions
  Dmitriy Drusvyatskiy and Lin Xiao
  Mathematics of Operations Research, 48(2):954-998, 2022.

• Stochastic variance-reduced prox-linear algorithms for nonconvex composite optimization
  Junyu Zhang and Lin Xiao
  Mathematical Programming, 195:649-691, 2022.

• On the convergence rates of policy gradient methods
  Lin Xiao
  Journal of Machine Learning Research, 23(282):1-36, 2022.

• BiT: Robustly Binarized Multi-distilled Transformer
  Zechun Liu, Barlas Oguz, Aasish Pappu, Lin Xiao, Scott Yih, Meng Li, Raghuraman Krishnamoorthi, Yashar Mehdad
  Advances in Neural Information Processing Systems (NeurIPS) 35/, 2022.

• Federated Learning with Partial Model Personalization
  Krishna Pillutla, Kshitiz Malik, Abdel-Rahman Mohamed, Mike Rabbat, Maziar Sanjabi, Lin Xiao
  ICML 2022.

• FedShuffle: Recipes for Better Use of Local Work in Federated Learning
  Samuel Horváth, Maziar Sanjabi, Lin Xiao, Peter Richtárik, Michael Rabbat
  Transactions of Machine Learning Research, 2022.

2021

• On self-concordant barriers for generalized power cones
  Scott Roy and Lin Xiao
  Optimization Letters, published online, June, 2021.

• From low probability to high confidence in stochastic convex optimization
  Damek Davis, Dmitriy Drusvyatskiy, Lin Xiao, and Junyu Zhang
  Journal of Machine Learning Research, 22(49):1-38, 2021.

• Accelerated Bregman proximal gradient methods for relatively smooth convex optimization
  Filip Hanely, Peter Richtarik, and Lin Xiao
  Computational Optimization and Applications, 79:405-440, 2021.

• MultiLevel Composite Stochastic Optimization via Nested Variance Reduction
  Junyu Zhang and Lin Xiao
  SIAM Journal on Optimization, 31(2):1131-1157, 2021.

• Adaptive stochastic variance reduction for subsampled Newton method with cubic regularization
  Junyu Zhang, Lin Xiao, and Shuzhong Zhang
  INFORMS Journal on Optimization, to appear, 2021.

2020

• Statistical Adaptive Stochastic Gradient Methods
  Pengchuan Zhang, Hunter Lang, Qiang Liu, and Lin Xiao
  arXiv preprint, 2020.

• Statistically Preconditioned Accelerated Gradient Method for Distributed Optimization
  Hadrien Hendrikx, Lin Xiao, Sebastien Bubeck, Francis Bach, Laurent Massoulie
  Proceedings of the 37th International Conference on Machine Learning, PMLR 119:4203-4227, 2020.

2019

• DSCOVR: Randomized Primal-Dual Block Coordinate Algorithms for Asynchronous Distributed Optimization
  Lin Xiao, Adams Wei Yu, Qihang Lin, Weizhu Chen
  Journal of Machine Learning Research, 20(43):1−58, 2019.

• Using Statistics to Automate Stochastic Optimization
  Hunter Lang, Lin Xiao, Pengchuan Zhang
  Advances in Neural Information Processing Systems (NeurIPS) 32, 2019.

• Understanding the Role of Momentum in Stochastic Gradient Methods
  Igor Gitman, Hunter Lang, Pengchuan Zhang, Lin Xiao
  Advances in Neural Information Processing Systems (NeurIPS) 32, 2019.

• Stochastic Composite Gradient Method with Incremental Variance Reduction
  Junyu Zhang, Lin Xiao
  Advances in Neural Information Processing Systems (NeurIPS) 32, 2019.

• A Composite Randomized Incremental Gradient Method
  Junyu Zhang, Lin Xiao
  Proceedings of the 36th International Conference on Machine Learning (ICML), PMLR 97:7454-7462, 2019.

2018

• Coupled Variational Bayes via Optimization Embedding
  Bo Dai, Hanjun Dai, Niao He, Weiyang Liu, Zhen Liu, Jianshu Chen, Lin Xiao, Le Song
  Advances in Neural Information Processing Systems (NeurIPS) 31, 2018.

• Learning SMaLL Predictors
  Vikas Garg, Ofer Dekel, Lin Xiao
  Advances in Neural Information Processing Systems (NeurIPS) 31, 2018.

• SBEED: Convergent Reinforcement Learning with Nonlinear Function Approximation
  Bo Dai, Albert Shaw, Lihong Li, Lin Xiao, Niao He, Zhen Liu, Jianshu Chen, Le Song
  Proceedings of the 35th International Conference on Machine Learning, PMLR 80:1125-1134, 2018.

• Sparse Multi-Prototype Classification
  Vikas K. Garg, Lin Xiao, Ofer Dekel
  Proceedings of the Conference on Uncetainty in Artifical Intelligence (UAI), 2018.

• Communication-Efficient Distributed Optimization of Self-Concordant Empirical Loss
  Yuchen Zhang and Lin Xiao
  Large-Scale and Distributed Optimization, Giselsson and Rantzer (Editors), pages 289-341, Springer, 2018.

2017

• Stochastic Primal-Dual Coordinate Method for Regularized Empirical Risk Minimization
  Yuchen Zhang and Lin Xiao
  Journal of Machine Learning Research, 18(84):1-42, 2017.

• Variational Gram functions: convex analysis and optimization
  Amin Jalali, Maryam Fazel, Lin Xiao
  SIAM Journal on Optimization, 27(4):634-2661, 2017.

• A Randomized Nonmonotone Block Proximal Gradient Method for a Class of Structured Nonlinear Programming
  Zhaosong Lu and Lin Xiao
  SIAM Journal on Numerical Analysis, 55(6):2930-2955, 2017.

• Q-LDA: Uncovering Latent Patterns in Text-based Sequential Decision Processes
  Jianshu Chen, Chong Wang, Lin Xiao, Ji He, Lihong Li, Li Deng
  Advances in Neural Information Processing Systems (NIPS) 30, 2017.

• Stochastic Variance Reduction Methods for Policy Evaluation
  Simon S. Du, Jianshu Chen, Lihong Li, Lin Xiao, Dengyong Zhou
  Proceedings of the 34th International Conference on Machine Learning, PMLR 70:1049-1058, 2017.

• Exploiting Strong Convexity from Data with Primal-Dual First-Order Algorithms
  Jialei Wang and Lin Xiao
  Proceedings of the 34th International Conference on Machine Learning, PMLR 70:3694-3702, 2017.

2015

• An Accelerated Randomized Proximal Coordinate Gradient Method and its Application to Regularized Empirical Risk Minimization
  Qihang Lin, Zhaosong Lu, and Lin Xiao
  SIAM Journal on Optimization, 25(4):2244–2273, 2015.

• On the Complexity Analysis of Randomized Block-Coordinate Descent Methods
  Zhaosong Lu and Lin Xiao
  Mathematical Programming, Series A, 152(1-2):15-642, 2015.

• An adaptive accelerated proximal gradient method and its homotopy continuation for sparse optimization
  Qihang Lin and Lin Xiao
  Computational Optimization and Applications, 60(3):633-674, 2015.

• End-to-end Learning of LDA by Mirror-Descent Back Propagation over a Deep Architecture
  Jianshu Chen, Ji He, Yelong Shen, Lin Xiao, Xiaodong He, Jianfeng Gao, Xinying Song, Li Deng
  Advances in Neural Information Processing Systems (NIPS) 28, 2015.

• Scaling Up Stochastic Dual Coordinate Ascent
  Kenneth Tran, Saghar Hosseini, Lin Xiao, Thomas Finley, Mikhail Bilenko
  Proceedings of the 21st ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), 2015.

• Stochastic Primal-Dual Coordinate Method for Regularized Empirical Risk Minimization
  Yuchen Zhang and Lin Xiao
  Proceedings of the 32nd International Conference on Machine Learning, PMLR 37:353-361, 2015.

• DiSCO: Distributed Optimization for Self-Concordant Empirical Loss
  Yuchen Zhang and Lin Xiao
  Proceedings of the 32nd International Conference on Machine Learning, PMLR 37:362-370, 2015.

2014

• A Proximal Stochastic Gradient Method with Progressive Variance Reduction
  Lin Xiao and Tong Zhang
  SIAM Journal on Optimization, 24(4):2057-2075, 2014.

• An Accelerated Proximal Coordinate Gradient Method
  Qihang Lin, Zhaosong Lu, Lin Xiao
  Advances in Neural Information Processing Systems (NIPS) 27, 2014.

• Online Classification Using a Voted RDA Method
  Tianbing Xu, Jianfeng Gao, Lin Xiao, Amelia Regan
  Proceedings of the 28th AAAI Conference on Artificial Intelligence, 2014.

• An Adaptive Accelerated Proximal Gradient Method and its Homotopy Continuation for Sparse Optimization
  Qihang Lin and Lin Xiao
  Proceedings of the 31st International Conference on Machine Learning (ICML), PMLR 32(1):73-81, 2014.

2013

• A Proximal-Gradient Homotopy Method for the Sparse Least-Squares Problem
  Lin Xiao and Tong Zhang
  SIAM Journal on Optimization, 23(2):1062-1091, 2013.

2012

• Optimal Distributed Online Prediction Using Mini-Batches
  Ofer Dekel, Ran Gilad-Bachrach, Ohad Shamir, Lin Xiao
  Journal of Machine Learning Research, 13(6):165−202, 2012.

• A Proximal-Gradient Homotopy Method for the L1-Regularized Least-Squares Problem
  Lin Xiao and Tong Zhang
  Proceedings of the 29th International Conference on Machine Learning (ICML), 2012.

2011

• Hierarchical Classification via Orthogonal Transfer
  Dengyong Zhou, Lin Xiao and Mingrui Wu
  Proceedings of the 28th International Conference on Machine Learning (ICML), 2011.

• Optimal Distributed Online Prediction
  Ofer Dekel, Ran Gilad-Bachrach, Ohad Shamir, Lin Xiao
  Proceedings of the 28th International Conference on Machine Learning (ICML), 2011.

• Distributed algorithms via gradient descent for fisher markets
  Benjamin Birnbaum, Nikhil R. Devanur, Lin Xiao
  Proceedings of the 12th ACM conference on Electronic Commerce, Pages 127-136, 2011.

2010

• Dual Averaging Methods for Regularized Stochastic Learning and Online Optimization
  Lin Xiao
  Journal of Machine Learning Research, 11(88):2543-2596, 2010.

• A Geometric Perspective of Large-Margin Training of Gaussian Models
  Lin Xiao and Li Deng
  IEEE Signal Processing Magazine, 27(6):118-123, 2010.

• Learning to classify with missing and corrupted features
  Ofer Dekel, Ohad Shamir, Lin Xiao
  Machine Learning, 81:149–178, 2010.

• Optimal Algorithms for Online Convex Optimization with Multi-Point Bandit Feedback
  Alekh Agarwal, Ofer Dekel, Lin Xiao
  The 23rd Annual Conference on Learning Theory (COLT), 2010.

2009

• Fastest Mixing Markov Chain on Graphs with Symmetries
  Stephen Boyd, Persi Diaconis, Pablo Parrilo, and Lin Xiao
  SIAM Journal on Optimization, 20(2):792-819, 2009.

• Dual Averaging Method for Regularized Stochastic Learning and Online Optimization
  Lin Xiao
  Advances in Neural Information Processing Systems (NIPS) 22, 2009.

2008

• Energy-Aware Server Provisioning and Load Dispatching for Connection-Intensive Internet Services
  Gong Chen, Wenbo He, Jie Liu, Suman Nath, Leonidas Rigas, Lin Xiao, Feng Zhao
  Proceedings of the 5th USENIX Symposium on Networked Systems Design and Implementation (NSDI’08), Pages 337-350, 2008.

2007

• Distributed average consensus with least-mean-square deviation
  Lin Xiao, Stephen Boyd, Seung-Jean Kim
  Journal of Parallel and Distributed Computing, 67(1):33-46, 2007.

2006

• The Fastest Mixing Markov Process on a Graph and a Connection to a Maximum Variance Unfolding Problem
  Jun Sun, Stephen Boyd, Lin Xiao, and Persi Diaconis
  SIAM Review, 48(4):681-699, 2006.

• Cross-layer optimization of wireless networks using nonlinear column generation
  Mikael Johansson and Lin Xiao
  IEEE Transactions on Wireless Communications, 5(2):435-445, 2006.

• Optimal Scaling of a Gradient Method for Distributed Resource Allocation
  Lin Xiao and Stephen Boyd
  Journal of Optimization Theory and Applications, 129:469-488, 2006.

• Fastest Mixing Markov Chain on a Path
  Stephen Boyd, Persi Diaconis, Jun Sun, Lin Xiao
  The American Mathematical Monthly, 113(1):70–74, 2006.

• A duality view of spectral methods for dimensionality reduction
  Lin Xiao, Jun Sun, Stephen Boyd
  Proceedings of the 23rd international conference on Machine learning (ICML), Pages 1041-1048, 2006.

• A space-time diffusion scheme for peer-to-peer least-squares estimation
  Lin Xiao, Stephen Boyd, Sanjay Lall
  Proceedings of the 5th International Conference on Information Processing in Sensor Networks (IPSN), 2006.

2005

• Least-Squares Covariance Matrix Adjustment
  Stephen Boyd and Lin Xiao
  SIAM Journal on Matrix Analysis and Applications, 27(2):532-546, 2005.

• Symmetry Analysis of Reversible Markov Chains
  Stephen Boyd, Persi Diaconis, Pablo Parrilo, and Lin Xiao
  Internet Mathematics, 2(1):31-71, 2005.

• Joint Optimization of Wireless Communication and Networked Control Systems
  Lin Xiao, Mikael Johansson, Haitham Hindi, Stephen Boyd and Andrea Goldsmith
  Switching and Learning in Feedback Systems, Murray-Smith and Shorten (eds), Lecture Notes in Computer Science, vol 3355, 2005.

• A scheme for robust distributed sensor fusion based on average consensus
  Lin Xiao, Stephen Boyd, Sanjay Lall
  Proceedings of the 4th International Conference on Information Processing in Sensor Networks (IPSN), 2005.

2004

• Fastest Mixing Markov Chain on a Graph
  Stephen Boyd, Persi Diaconis, and Lin Xiao
  SIAM Review, 46(4):667-689, 2004.

• Fast linear iterations for distributed averaging
  Lin Xiao and Stephen Boyd
  Systems & Control Letters, 53(1):65-78, 2004.

• Simultaneous routing and resource allocation via dual decomposition
  Lin Xiao, Mikael Johansson, Stephey Boyd
  IEEE Transactions on Communications, 52(7):1136-1144, July 2004.

• A decomposition approach to distributed analysis of networked systems
  Cedric Langbort, Lin Xiao, Raffaello D’Andrea, Stephen Boyd
  Proceedings of the 43rd IEEE Conference on Decision and Control (CDC), 2004.

• Scheduling, routing and power allocation for fairness in wireless networks
  Mikael Johansson and Lin Xiao
  Proceedings of IEEE 59th Vehicular Technology Conference, 2004.

2003

• Joint optimization of communication rates and linear systems
  Lin Xiao, Mikael Johansson, Haitham Hindi, Stephen Boyd, Andrea Goldsmith
  IEEE Transactions on Automatic Control, 48(1):148-153, 2003.

• Fast linear iterations for distributed averaging
  Lin Xiao and Stephen Boyd
  Proceedings of the 42nd IEEE International Conference on Decision and Control (CDC), 2003.

• Simultaneous Routing and Resource Allocation in CDMA Wireless Data Networks
  Mikael Johansson, Lin Xiao, Stephen Boyd
  Proceedings of IEEE International Conference on Communications, Anchorage, Alaska, May 2003.

2000

• Control with random communication delays via a discrete-time jump system approach
  Lin Xiao, Arash Hassibi, Jonathan P. How
  Proceedings of the 2000 American Control Conference (ACC), 2000.