Unveiling Transformers with LEGO: a synthetic reasoning task
Yi Zhang, Arturs Backurs, Sébastien Bubeck, Ronen Eldan, Suriya Gunasekar, Tal Wagner
June 2022
Foundations of Optimization
Publications
Publications par année
-
-
Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning
Zeyuan Allen-Zhu, Yuanzhi Li, Zeyuan Allen-Zhu
arXiv preprint | December 2020, (2012.09816)
Backward Feature Correction: How Deep Learning Performs Deep Learning
Zeyuan Allen-Zhu, Yuanzhi Li
June 2020
Stochastic Variance-Reduced Prox-Linear Algorithms for Nonconvex Composite Optimization
Junyu Zhang, Lin Xiao
MSR-TR-2020-11 | April 2020
Publié par Microsoft
Statistically Preconditioned Accelerated Gradient Method for Distributed Optimization
Hadrien Hendrikx, Lin Xiao (lixiao), Sébastien Bubeck (sebubeck), Francis Bach, Laurent Massoulie
MSR-TR-2020-5 | February 2020
Publié par Microsoft Research
-
A Stochastic Composite Gradient Method with Incremental Variance Reduction
Junyu Zhang, Lin Xiao
Neural Information Processing Systems | December 2019
A Stochastic Composite Gradient Method with Incremental Variance Reduction
Lin Xiao (lixiao), Junyu Zhang
Neural Information Processing Systems | December 2019
Efficiency of Line Search in Proximal Gradient Methods
Lin Xiao
MSR-TR-2019-28 | November 2019
Publié par Microsoft
From low probability to high confidence in stochastic convex optimization
Damek Davis, Dmitriy Drusvyatskiy, Lin Xiao, Junyu Zhang
October 2019
Multi-Level Composite Stochastic Optimization via Nested Variance Reduction
Junyu Zhang, Lin Xiao
August 2019
-
Coupled Variational Bayes via Optimization Embedding
Bo Dai, Hanjun Dai, Niao He, Weiyang Liu, Zhen Liu, Jianshu Chen, Lin Xiao, Le Song
Neural Information Processing Systems | December 2018
A Convergence Theory for Deep Learning via Over-Parameterization
Zeyuan Allen-Zhu, Yuanzhi Li, Zhao Song
September 2018
Accelerated Bregman Proximal Gradient Methods for Relatively Smooth Convex Optimization
Filip Hanzely, Peter Richtarik, Lin Xiao
MSR-TR-2018-22 | August 2018
Publié par Microsoft
Revised April 23, 2020.
Sparse Multi-Prototype Classification
Vikas K. Garg, Lin Xiao, Ofer Dekel
Proceedings of the Conference on Uncertainty in Artifical Intelligence (UAI) 2018 | August 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 International Conference on Machine Learning (ICML), 2018 | July 2018
Optimal Algorithms for Non-Smooth Distributed Optimization in Networks
Kevin Scaman, Francis Bach, Sébastien Bubeck, Yin Tat Lee, Laurent Massoulié
NeurIPS 2018 | June 2018
Best Paper Award
On self-concordant barriers for generalized power cones
Scott Roy, Lin Xiao (lixiao)
MSR-TR-2018-3 | January 2018
-
Q-LDA: Uncovering Latent Patterns in Text-based Sequential Decision Processes
Jianshu Chen (jianshuc), Chong Wang, Lin Xiao (lixiao), Ji He, Lihong Li, Li Deng
Advances in Neural Information Processing Systems (NIPS) 29 | December 2017
DSCOVR: Randomized Primal-Dual Block Coordinate Algorithms for Asynchronous Distributed Optimization
Lin Xiao (lixiao), Adams Wei Yu, Qihang Lin, Weizhu Chen
MSR-TR-2017-42 | October 2017
Variational Gram Functions: Convex Analysis and Optimization
Amin Jalali, Maryam Fazel, Lin Xiao
SIAM Journal on Optimization | October 2017
Stochastic Variance Reduction Methods for Policy Evaluation
Simon Du, Jianshu Chen, Lihong Li, Lin Xiao, Denny Zhou
Proceedings of the 34th International Conference on Machine Learning (ICML) | August 2017
Follow the Compressed Leader: Faster Online Learning of Eigenvectors and Faster MMWU
Zeyuan Allen-Zhu, Yuanzhi Li
June 2017
Online Auctions and Multi-scale Online Learning
Sébastien Bubeck, Nikhil Devanur, Zhiyi Huang, Rad Niazadeh
18th ACM conference on Economics and Computation (EC'17) | May 2017
Local Max-Cut In Smoothed Polynomial Time
Omer Angel, Sébastien Bubeck, Yuval Peres, Fan Wei
April 2017
Exploiting Strong Convexity from Data with Primal-Dual First-Order Algorithms
Jialei Wang, Lin Xiao
MSR-TR-2017-13 | March 2017
Natasha: Faster Non-Convex Stochastic Optimization Via Strongly Non-Convex Parameter
Zeyuan Allen-Zhu
February 2017
Linear Learning with Sparse Data
Ofer Dekel
January 2017
-
Linear Coupling: An Ultimate Unification of Gradient and Mirror Descent
Zeyuan Allen-Zhu, Lorenzo Orecchia
November 2016
First Efficient Convergence for Streaming k-PCA: a Global, Gap-Free, and Near-Optimal Rate
Zeyuan Allen-Zhu, Yuanzhi Li
July 2016
Tight Lower Bounds for Multiplicative Weights Algorithmic Families
Nick Gravin, Yuval Peres, Balasubramanian Sivan
July 2016
Kernel-Based Methods For Bandit Convex Optimization
Sébastien Bubeck, Ronen Eldan, Yin Tat Lee
July 2016
Towards Optimal Algorithms for Prediction with Expert Advice
Nick Gravin, Yuval Peres, Balasubramanian Sivan
July 2016
Katyusha: The First Direct Acceleration of Stochastic Gradient Methods
Zeyuan Allen-Zhu
March 2016
-
An Accelerated Randomized Proximal Coordinate Gradient Method and its Application to Regularized Empirical Risk Minimization
Qihang Lin, Zhaosong Lu, Lin Xiao
SIAM Journal on Optimization | November 2015
Multi-Scale Exploration of Convex Functions and Bandit Convex Optimization
Sébastien Bubeck, Ronen Eldan
arXiv:1507.06580v1 [math.MG] | July 2015
Best Paper Award
Sampling from a log-concave distribution with Projected Langevin Monte Carlo
Sébastien Bubeck, Ronen Eldan, Joseph Lehec
July 2015
A Geometric Alternative To Nesterov’s Accelerated Gradient Descent
Sébastien Bubeck, Yin Tat Lee, Mohit Singh
June 2015
The Entropic Barrier: A Simple and Optimal Universal Self-Concordant Barrier
Sébastien Bubeck, Ronen Eldan
April 2015
Bandit Convex Optimization: sqrt{T} Regret in One Dimension
Sébastien Bubeck, Ofer Dekel, Tomer Koren, Yuval Peres
February 2015
Communication-Efficient Distributed Optimization of Self-Concordant Empirical Loss
Yuchen Zhang, Lin Xiao
MSR-TR-2015-1 | January 2015
-
Stochastic Primal-Dual Coordinate Method for Regularized Empirical Risk Minimization
Yuchen Zhang, Lin Xiao
MSR-TR-2014-123 | September 2014
Bandits with Switching Costs: T 2/3 Regret
Ofer Dekel, Jian Ding, Tomer Koren, Yuval Peres
In Proceedings of the 46th Annual Symposium on the Theory of Computing, 2014 | May 2014
A Proximal Stochastic Gradient Method with Progressive Variance Reduction
Lin Xiao
MSR-TR-2014-38 | March 2014
-
Finding Hidden Cliques in Linear Time with High Probability
Yael Dekel, Ori Gurel-Gurevich, Yuval Peres
October 2010
Filtre par zone de recherche
-
Unveiling Transformers with LEGO: a synthetic reasoning task
Yi Zhang, Arturs Backurs, Sébastien Bubeck, Ronen Eldan, Suriya Gunasekar, Tal Wagner
June 2022
Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning
Zeyuan Allen-Zhu, Yuanzhi Li, Zeyuan Allen-Zhu
arXiv preprint | December 2020, (2012.09816)
Backward Feature Correction: How Deep Learning Performs Deep Learning
Zeyuan Allen-Zhu, Yuanzhi Li
June 2020
Stochastic Variance-Reduced Prox-Linear Algorithms for Nonconvex Composite Optimization
Junyu Zhang, Lin Xiao
MSR-TR-2020-11 | April 2020
Publié par Microsoft
Statistically Preconditioned Accelerated Gradient Method for Distributed Optimization
Hadrien Hendrikx, Lin Xiao (lixiao), Sébastien Bubeck (sebubeck), Francis Bach, Laurent Massoulie
MSR-TR-2020-5 | February 2020
Publié par Microsoft Research
A Stochastic Composite Gradient Method with Incremental Variance Reduction
Junyu Zhang, Lin Xiao
Neural Information Processing Systems | December 2019
A Stochastic Composite Gradient Method with Incremental Variance Reduction
Lin Xiao (lixiao), Junyu Zhang
Neural Information Processing Systems | December 2019
Efficiency of Line Search in Proximal Gradient Methods
Lin Xiao
MSR-TR-2019-28 | November 2019
Publié par Microsoft
From low probability to high confidence in stochastic convex optimization
Damek Davis, Dmitriy Drusvyatskiy, Lin Xiao, Junyu Zhang
October 2019
Multi-Level Composite Stochastic Optimization via Nested Variance Reduction
Junyu Zhang, Lin Xiao
August 2019
Coupled Variational Bayes via Optimization Embedding
Bo Dai, Hanjun Dai, Niao He, Weiyang Liu, Zhen Liu, Jianshu Chen, Lin Xiao, Le Song
Neural Information Processing Systems | December 2018
Accelerated Bregman Proximal Gradient Methods for Relatively Smooth Convex Optimization
Filip Hanzely, Peter Richtarik, Lin Xiao
MSR-TR-2018-22 | August 2018
Publié par Microsoft
Revised April 23, 2020.
Sparse Multi-Prototype Classification
Vikas K. Garg, Lin Xiao, Ofer Dekel
Proceedings of the Conference on Uncertainty in Artifical Intelligence (UAI) 2018 | August 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 International Conference on Machine Learning (ICML), 2018 | July 2018
Optimal Algorithms for Non-Smooth Distributed Optimization in Networks
Kevin Scaman, Francis Bach, Sébastien Bubeck, Yin Tat Lee, Laurent Massoulié
NeurIPS 2018 | June 2018
Best Paper Award
On self-concordant barriers for generalized power cones
Scott Roy, Lin Xiao (lixiao)
MSR-TR-2018-3 | January 2018
Q-LDA: Uncovering Latent Patterns in Text-based Sequential Decision Processes
Jianshu Chen (jianshuc), Chong Wang, Lin Xiao (lixiao), Ji He, Lihong Li, Li Deng
Advances in Neural Information Processing Systems (NIPS) 29 | December 2017
DSCOVR: Randomized Primal-Dual Block Coordinate Algorithms for Asynchronous Distributed Optimization
Lin Xiao (lixiao), Adams Wei Yu, Qihang Lin, Weizhu Chen
MSR-TR-2017-42 | October 2017
Variational Gram Functions: Convex Analysis and Optimization
Amin Jalali, Maryam Fazel, Lin Xiao
SIAM Journal on Optimization | October 2017
Stochastic Variance Reduction Methods for Policy Evaluation
Simon Du, Jianshu Chen, Lihong Li, Lin Xiao, Denny Zhou
Proceedings of the 34th International Conference on Machine Learning (ICML) | August 2017
Follow the Compressed Leader: Faster Online Learning of Eigenvectors and Faster MMWU
Zeyuan Allen-Zhu, Yuanzhi Li
June 2017
Online Auctions and Multi-scale Online Learning
Sébastien Bubeck, Nikhil Devanur, Zhiyi Huang, Rad Niazadeh
18th ACM conference on Economics and Computation (EC'17) | May 2017
Local Max-Cut In Smoothed Polynomial Time
Omer Angel, Sébastien Bubeck, Yuval Peres, Fan Wei
April 2017
Exploiting Strong Convexity from Data with Primal-Dual First-Order Algorithms
Jialei Wang, Lin Xiao
MSR-TR-2017-13 | March 2017
Natasha: Faster Non-Convex Stochastic Optimization Via Strongly Non-Convex Parameter
Zeyuan Allen-Zhu
February 2017
Linear Learning with Sparse Data
Ofer Dekel
January 2017
Linear Coupling: An Ultimate Unification of Gradient and Mirror Descent
Zeyuan Allen-Zhu, Lorenzo Orecchia
November 2016
First Efficient Convergence for Streaming k-PCA: a Global, Gap-Free, and Near-Optimal Rate
Zeyuan Allen-Zhu, Yuanzhi Li
July 2016
Tight Lower Bounds for Multiplicative Weights Algorithmic Families
Nick Gravin, Yuval Peres, Balasubramanian Sivan
July 2016
Kernel-Based Methods For Bandit Convex Optimization
Sébastien Bubeck, Ronen Eldan, Yin Tat Lee
July 2016
Towards Optimal Algorithms for Prediction with Expert Advice
Nick Gravin, Yuval Peres, Balasubramanian Sivan
July 2016
Katyusha: The First Direct Acceleration of Stochastic Gradient Methods
Zeyuan Allen-Zhu
March 2016
An Accelerated Randomized Proximal Coordinate Gradient Method and its Application to Regularized Empirical Risk Minimization
Qihang Lin, Zhaosong Lu, Lin Xiao
SIAM Journal on Optimization | November 2015
Multi-Scale Exploration of Convex Functions and Bandit Convex Optimization
Sébastien Bubeck, Ronen Eldan
arXiv:1507.06580v1 [math.MG] | July 2015
Best Paper Award
Sampling from a log-concave distribution with Projected Langevin Monte Carlo
Sébastien Bubeck, Ronen Eldan, Joseph Lehec
July 2015
A Geometric Alternative To Nesterov’s Accelerated Gradient Descent
Sébastien Bubeck, Yin Tat Lee, Mohit Singh
June 2015
Communication-Efficient Distributed Optimization of Self-Concordant Empirical Loss
Yuchen Zhang, Lin Xiao
MSR-TR-2015-1 | January 2015
Stochastic Primal-Dual Coordinate Method for Regularized Empirical Risk Minimization
Yuchen Zhang, Lin Xiao
MSR-TR-2014-123 | September 2014
A Proximal Stochastic Gradient Method with Progressive Variance Reduction
Lin Xiao
MSR-TR-2014-38 | March 2014
-
Unveiling Transformers with LEGO: a synthetic reasoning task
Yi Zhang, Arturs Backurs, Sébastien Bubeck, Ronen Eldan, Suriya Gunasekar, Tal Wagner
June 2022
Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning
Zeyuan Allen-Zhu, Yuanzhi Li, Zeyuan Allen-Zhu
arXiv preprint | December 2020, (2012.09816)
Backward Feature Correction: How Deep Learning Performs Deep Learning
Zeyuan Allen-Zhu, Yuanzhi Li
June 2020
Statistically Preconditioned Accelerated Gradient Method for Distributed Optimization
Hadrien Hendrikx, Lin Xiao (lixiao), Sébastien Bubeck (sebubeck), Francis Bach, Laurent Massoulie
MSR-TR-2020-5 | February 2020
Publié par Microsoft Research
A Stochastic Composite Gradient Method with Incremental Variance Reduction
Junyu Zhang, Lin Xiao
Neural Information Processing Systems | December 2019
A Stochastic Composite Gradient Method with Incremental Variance Reduction
Lin Xiao (lixiao), Junyu Zhang
Neural Information Processing Systems | December 2019
Coupled Variational Bayes via Optimization Embedding
Bo Dai, Hanjun Dai, Niao He, Weiyang Liu, Zhen Liu, Jianshu Chen, Lin Xiao, Le Song
Neural Information Processing Systems | December 2018
A Convergence Theory for Deep Learning via Over-Parameterization
Zeyuan Allen-Zhu, Yuanzhi Li, Zhao Song
September 2018
Sparse Multi-Prototype Classification
Vikas K. Garg, Lin Xiao, Ofer Dekel
Proceedings of the Conference on Uncertainty in Artifical Intelligence (UAI) 2018 | August 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 International Conference on Machine Learning (ICML), 2018 | July 2018
Q-LDA: Uncovering Latent Patterns in Text-based Sequential Decision Processes
Jianshu Chen (jianshuc), Chong Wang, Lin Xiao (lixiao), Ji He, Lihong Li, Li Deng
Advances in Neural Information Processing Systems (NIPS) 29 | December 2017
DSCOVR: Randomized Primal-Dual Block Coordinate Algorithms for Asynchronous Distributed Optimization
Lin Xiao (lixiao), Adams Wei Yu, Qihang Lin, Weizhu Chen
MSR-TR-2017-42 | October 2017
Stochastic Variance Reduction Methods for Policy Evaluation
Simon Du, Jianshu Chen, Lihong Li, Lin Xiao, Denny Zhou
Proceedings of the 34th International Conference on Machine Learning (ICML) | August 2017
Exploiting Strong Convexity from Data with Primal-Dual First-Order Algorithms
Jialei Wang, Lin Xiao
MSR-TR-2017-13 | March 2017
An Accelerated Randomized Proximal Coordinate Gradient Method and its Application to Regularized Empirical Risk Minimization
Qihang Lin, Zhaosong Lu, Lin Xiao
SIAM Journal on Optimization | November 2015
Communication-Efficient Distributed Optimization of Self-Concordant Empirical Loss
Yuchen Zhang, Lin Xiao
MSR-TR-2015-1 | January 2015
Stochastic Primal-Dual Coordinate Method for Regularized Empirical Risk Minimization
Yuchen Zhang, Lin Xiao
MSR-TR-2014-123 | September 2014
Bandits with Switching Costs: T 2/3 Regret
Ofer Dekel, Jian Ding, Tomer Koren, Yuval Peres
In Proceedings of the 46th Annual Symposium on the Theory of Computing, 2014 | May 2014
A Proximal Stochastic Gradient Method with Progressive Variance Reduction
Lin Xiao
MSR-TR-2014-38 | March 2014
-
Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning
Zeyuan Allen-Zhu, Yuanzhi Li, Zeyuan Allen-Zhu
arXiv preprint | December 2020, (2012.09816)
Backward Feature Correction: How Deep Learning Performs Deep Learning
Zeyuan Allen-Zhu, Yuanzhi Li
June 2020
Statistically Preconditioned Accelerated Gradient Method for Distributed Optimization
Hadrien Hendrikx, Lin Xiao (lixiao), Sébastien Bubeck (sebubeck), Francis Bach, Laurent Massoulie
MSR-TR-2020-5 | February 2020
Publié par Microsoft Research
From low probability to high confidence in stochastic convex optimization
Damek Davis, Dmitriy Drusvyatskiy, Lin Xiao, Junyu Zhang
October 2019
Multi-Level Composite Stochastic Optimization via Nested Variance Reduction
Junyu Zhang, Lin Xiao
August 2019
Accelerated Bregman Proximal Gradient Methods for Relatively Smooth Convex Optimization
Filip Hanzely, Peter Richtarik, Lin Xiao
MSR-TR-2018-22 | August 2018
Publié par Microsoft
Revised April 23, 2020.
On self-concordant barriers for generalized power cones
Scott Roy, Lin Xiao (lixiao)
MSR-TR-2018-3 | January 2018
DSCOVR: Randomized Primal-Dual Block Coordinate Algorithms for Asynchronous Distributed Optimization
Lin Xiao (lixiao), Adams Wei Yu, Qihang Lin, Weizhu Chen
MSR-TR-2017-42 | October 2017
Variational Gram Functions: Convex Analysis and Optimization
Amin Jalali, Maryam Fazel, Lin Xiao
SIAM Journal on Optimization | October 2017
Follow the Compressed Leader: Faster Online Learning of Eigenvectors and Faster MMWU
Zeyuan Allen-Zhu, Yuanzhi Li
June 2017
Local Max-Cut In Smoothed Polynomial Time
Omer Angel, Sébastien Bubeck, Yuval Peres, Fan Wei
April 2017
Exploiting Strong Convexity from Data with Primal-Dual First-Order Algorithms
Jialei Wang, Lin Xiao
MSR-TR-2017-13 | March 2017
Linear Coupling: An Ultimate Unification of Gradient and Mirror Descent
Zeyuan Allen-Zhu, Lorenzo Orecchia
November 2016
First Efficient Convergence for Streaming k-PCA: a Global, Gap-Free, and Near-Optimal Rate
Zeyuan Allen-Zhu, Yuanzhi Li
July 2016
The Entropic Barrier: A Simple and Optimal Universal Self-Concordant Barrier
Sébastien Bubeck, Ronen Eldan
April 2015
Bandit Convex Optimization: sqrt{T} Regret in One Dimension
Sébastien Bubeck, Ofer Dekel, Tomer Koren, Yuval Peres
February 2015
Finding Hidden Cliques in Linear Time with High Probability
Yael Dekel, Ori Gurel-Gurevich, Yuval Peres
October 2010
Publication Type
-
Unveiling Transformers with LEGO: a synthetic reasoning task
Yi Zhang, Arturs Backurs, Sébastien Bubeck, Ronen Eldan, Suriya Gunasekar, Tal Wagner
June 2022
-
Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning
Zeyuan Allen-Zhu, Yuanzhi Li, Zeyuan Allen-Zhu
arXiv preprint | December 2020, (2012.09816)
Variational Gram Functions: Convex Analysis and Optimization
Amin Jalali, Maryam Fazel, Lin Xiao
SIAM Journal on Optimization | October 2017
Local Max-Cut In Smoothed Polynomial Time
Omer Angel, Sébastien Bubeck, Yuval Peres, Fan Wei
April 2017
Natasha: Faster Non-Convex Stochastic Optimization Via Strongly Non-Convex Parameter
Zeyuan Allen-Zhu
February 2017
Linear Learning with Sparse Data
Ofer Dekel
January 2017
Linear Coupling: An Ultimate Unification of Gradient and Mirror Descent
Zeyuan Allen-Zhu, Lorenzo Orecchia
November 2016
Tight Lower Bounds for Multiplicative Weights Algorithmic Families
Nick Gravin, Yuval Peres, Balasubramanian Sivan
July 2016
Towards Optimal Algorithms for Prediction with Expert Advice
Nick Gravin, Yuval Peres, Balasubramanian Sivan
July 2016
Katyusha: The First Direct Acceleration of Stochastic Gradient Methods
Zeyuan Allen-Zhu
March 2016
An Accelerated Randomized Proximal Coordinate Gradient Method and its Application to Regularized Empirical Risk Minimization
Qihang Lin, Zhaosong Lu, Lin Xiao
SIAM Journal on Optimization | November 2015
Sampling from a log-concave distribution with Projected Langevin Monte Carlo
Sébastien Bubeck, Ronen Eldan, Joseph Lehec
July 2015
The Entropic Barrier: A Simple and Optimal Universal Self-Concordant Barrier
Sébastien Bubeck, Ronen Eldan
April 2015
Bandit Convex Optimization: sqrt{T} Regret in One Dimension
Sébastien Bubeck, Ofer Dekel, Tomer Koren, Yuval Peres
February 2015
Finding Hidden Cliques in Linear Time with High Probability
Yael Dekel, Ori Gurel-Gurevich, Yuval Peres
October 2010
-
Backward Feature Correction: How Deep Learning Performs Deep Learning
Zeyuan Allen-Zhu, Yuanzhi Li
June 2020
From low probability to high confidence in stochastic convex optimization
Damek Davis, Dmitriy Drusvyatskiy, Lin Xiao, Junyu Zhang
October 2019
Multi-Level Composite Stochastic Optimization via Nested Variance Reduction
Junyu Zhang, Lin Xiao
August 2019
A Convergence Theory for Deep Learning via Over-Parameterization
Zeyuan Allen-Zhu, Yuanzhi Li, Zhao Song
September 2018
-
Stochastic Variance-Reduced Prox-Linear Algorithms for Nonconvex Composite Optimization
Junyu Zhang, Lin Xiao
MSR-TR-2020-11 | April 2020
Publié par Microsoft
Statistically Preconditioned Accelerated Gradient Method for Distributed Optimization
Hadrien Hendrikx, Lin Xiao (lixiao), Sébastien Bubeck (sebubeck), Francis Bach, Laurent Massoulie
MSR-TR-2020-5 | February 2020
Publié par Microsoft Research
Efficiency of Line Search in Proximal Gradient Methods
Lin Xiao
MSR-TR-2019-28 | November 2019
Publié par Microsoft
Accelerated Bregman Proximal Gradient Methods for Relatively Smooth Convex Optimization
Filip Hanzely, Peter Richtarik, Lin Xiao
MSR-TR-2018-22 | August 2018
Publié par Microsoft
Revised April 23, 2020.
On self-concordant barriers for generalized power cones
Scott Roy, Lin Xiao (lixiao)
MSR-TR-2018-3 | January 2018
DSCOVR: Randomized Primal-Dual Block Coordinate Algorithms for Asynchronous Distributed Optimization
Lin Xiao (lixiao), Adams Wei Yu, Qihang Lin, Weizhu Chen
MSR-TR-2017-42 | October 2017
Exploiting Strong Convexity from Data with Primal-Dual First-Order Algorithms
Jialei Wang, Lin Xiao
MSR-TR-2017-13 | March 2017
Communication-Efficient Distributed Optimization of Self-Concordant Empirical Loss
Yuchen Zhang, Lin Xiao
MSR-TR-2015-1 | January 2015
Stochastic Primal-Dual Coordinate Method for Regularized Empirical Risk Minimization
Yuchen Zhang, Lin Xiao
MSR-TR-2014-123 | September 2014
A Proximal Stochastic Gradient Method with Progressive Variance Reduction
Lin Xiao
MSR-TR-2014-38 | March 2014
-
A Stochastic Composite Gradient Method with Incremental Variance Reduction
Junyu Zhang, Lin Xiao
Neural Information Processing Systems | December 2019
A Stochastic Composite Gradient Method with Incremental Variance Reduction
Lin Xiao (lixiao), Junyu Zhang
Neural Information Processing Systems | December 2019
Coupled Variational Bayes via Optimization Embedding
Bo Dai, Hanjun Dai, Niao He, Weiyang Liu, Zhen Liu, Jianshu Chen, Lin Xiao, Le Song
Neural Information Processing Systems | December 2018
Sparse Multi-Prototype Classification
Vikas K. Garg, Lin Xiao, Ofer Dekel
Proceedings of the Conference on Uncertainty in Artifical Intelligence (UAI) 2018 | August 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 International Conference on Machine Learning (ICML), 2018 | July 2018
Optimal Algorithms for Non-Smooth Distributed Optimization in Networks
Kevin Scaman, Francis Bach, Sébastien Bubeck, Yin Tat Lee, Laurent Massoulié
NeurIPS 2018 | June 2018
Best Paper Award
Q-LDA: Uncovering Latent Patterns in Text-based Sequential Decision Processes
Jianshu Chen (jianshuc), Chong Wang, Lin Xiao (lixiao), Ji He, Lihong Li, Li Deng
Advances in Neural Information Processing Systems (NIPS) 29 | December 2017
Stochastic Variance Reduction Methods for Policy Evaluation
Simon Du, Jianshu Chen, Lihong Li, Lin Xiao, Denny Zhou
Proceedings of the 34th International Conference on Machine Learning (ICML) | August 2017
Follow the Compressed Leader: Faster Online Learning of Eigenvectors and Faster MMWU
Zeyuan Allen-Zhu, Yuanzhi Li
June 2017
Online Auctions and Multi-scale Online Learning
Sébastien Bubeck, Nikhil Devanur, Zhiyi Huang, Rad Niazadeh
18th ACM conference on Economics and Computation (EC'17) | May 2017
First Efficient Convergence for Streaming k-PCA: a Global, Gap-Free, and Near-Optimal Rate
Zeyuan Allen-Zhu, Yuanzhi Li
July 2016
Kernel-Based Methods For Bandit Convex Optimization
Sébastien Bubeck, Ronen Eldan, Yin Tat Lee
July 2016
Multi-Scale Exploration of Convex Functions and Bandit Convex Optimization
Sébastien Bubeck, Ronen Eldan
arXiv:1507.06580v1 [math.MG] | July 2015
Best Paper Award
A Geometric Alternative To Nesterov’s Accelerated Gradient Descent
Sébastien Bubeck, Yin Tat Lee, Mohit Singh
June 2015
Bandits with Switching Costs: T 2/3 Regret
Ofer Dekel, Jian Ding, Tomer Koren, Yuval Peres
In Proceedings of the 46th Annual Symposium on the Theory of Computing, 2014 | May 2014