Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Tianyi Lin

Fast Distributionally Robust Learning with Variance Reduced Min-Max Optimization


Apr 27, 2021
Yaodong Yu, Tianyi Lin, Eric Mazumdar, Michael I. Jordan

* The first three authors contributed equally to this work; 37 pages, 20 figures 

  Access Paper or Ask Questions

A Variational Inequality Approach to Bayesian Regression Games


Mar 24, 2021
Wenshuo Guo, Michael I. Jordan, Tianyi Lin


  Access Paper or Ask Questions

Projection Robust Wasserstein Distance and Riemannian Optimization


Jun 28, 2020
Tianyi Lin, Chenyou Fan, Nhat Ho, Marco Cuturi, Michael I. Jordan

* The first two authors contributed equally 

  Access Paper or Ask Questions

On Projection Robust Optimal Transport: Sample Complexity and Model Misspecification


Jun 26, 2020
Tianyi Lin, Zeyu Zheng, Elynn Y. Chen, Marco Cuturi, Michael I. Jordan

* Correct some typos; 46 Pages, 41 figures 

  Access Paper or Ask Questions

Finite-Time Last-Iterate Convergence for Multi-Agent Learning in Games


Mar 18, 2020
Tianyi Lin, Zhengyuan Zhou, Panayotis Mertikopoulos, Michael I. Jordan

* Correct some typos 

  Access Paper or Ask Questions

Revisiting Fixed Support Wasserstein Barycenter: Computational Hardness and Efficient Algorithms


Mar 18, 2020
Tianyi Lin, Nhat Ho, Xi Chen, Marco Cuturi, Michael I. Jordan

* Correct some typos 

  Access Paper or Ask Questions

Near-Optimal Algorithms for Minimax Optimization


Feb 05, 2020
Tianyi Lin, Chi Jin, Michael. I. Jordan

* 40 pages 

  Access Paper or Ask Questions

On the Complexity of Approximating Multimarginal Optimal Transport


Sep 30, 2019
Tianyi Lin, Nhat Ho, Marco Cuturi, Michael I. Jordan

* 30 pages. The first two authors contributed equally to this work 

  Access Paper or Ask Questions

On the Acceleration of the Sinkhorn and Greenkhorn Algorithms for Optimal Transport


Jun 09, 2019
Tianyi Lin, Nhat Ho, Michael I. Jordan

* 31 pages, 36 figures. arXiv admin note: text overlap with arXiv:1901.06482 

  Access Paper or Ask Questions

On Gradient Descent Ascent for Nonconvex-Concave Minimax Problems


Jun 02, 2019
Tianyi Lin, Chi Jin, Michael I. Jordan


  Access Paper or Ask Questions

Global Error Bounds and Linear Convergence for Gradient-Based Algorithms for Trend Filtering and $\ell_{1}$-Convex Clustering


Apr 16, 2019
Nhat Ho, Tianyi Lin, Michael I. Jordan

* The first two authors contributed equally to this work 

  Access Paper or Ask Questions

Sparsemax and Relaxed Wasserstein for Topic Sparsity


Oct 22, 2018
Tianyi Lin, Zhiyue Hu, Xin Guo

* 9 Pages. To appear in WSDM 2019 

  Access Paper or Ask Questions

Relaxed Wasserstein with Applications to GANs


Sep 16, 2018
Xin Guo, Johnny Hong, Tianyi Lin, Nan Yang

* 29 pages; Revise and Remove Some Typos 

  Access Paper or Ask Questions

Improved Oracle Complexity of Variance Reduced Methods for Nonsmooth Convex Stochastic Composition Optimization


Jul 25, 2018
Tianyi Lin, Chenyou Fan, Mengdi Wang

* The error appears in the proof. More specifically, the proof of "section 3, Theorem 3.9" in the appendix has an error (c.f. Lemma B.4). Also some errors in "section 4, experiment". We have a new version arXiv:1806.00458 

  Access Paper or Ask Questions

Improved Oracle Complexity for Stochastic Compositional Variance Reduced Gradient


Jun 01, 2018
Tianyi Lin, Chenyou Fan, Mengdi Wang, Michael I. Jordan

* arXiv admin note: text overlap with arXiv: 1802.02339; correct typos, improve proof and add experiments on real datasets 

  Access Paper or Ask Questions

Stochastic Primal-Dual Proximal ExtraGradient Descent for Compositely Regularized Optimization


Feb 01, 2018
Tianyi Lin, Linbo Qiao, Teng Zhang, Jiashi Feng, Bofeng Zhang


  Access Paper or Ask Questions

On the Iteration Complexity Analysis of Stochastic Primal-Dual Hybrid Gradient Approach with High Probability


Feb 01, 2018
Linbo Qiao, Tianyi Lin, Qi Qin, Xicheng Lu


  Access Paper or Ask Questions

Structured Nonconvex and Nonsmooth Optimization: Algorithms and Iteration Complexity Analysis


Jan 17, 2018
Bo Jiang, Tianyi Lin, Shiqian Ma, Shuzhong Zhang

* Section 4.1 is updated 

  Access Paper or Ask Questions

Global Convergence of Unmodified 3-Block ADMM for a Class of Convex Minimization Problems


Jan 17, 2018
Tianyi Lin, Shiqian Ma, Shuzhong Zhang


  Access Paper or Ask Questions

An Extragradient-Based Alternating Direction Method for Convex Minimization


Jul 09, 2015
Tianyi Lin, Shiqian Ma, Shuzhong Zhang


  Access Paper or Ask Questions