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 Kaiyi Ji

Provably Faster Algorithms for Bilevel Optimization


Jun 08, 2021
Junjie Yang, Kaiyi Ji, Yingbin Liang

* This paper was submitted in May 2021 for publication 

  Access Paper or Ask Questions

Lower Bounds and Accelerated Algorithms for Bilevel Optimization


Feb 07, 2021
Kaiyi Ji, Yingbin Liang

* 33 pages, 1 Table 

  Access Paper or Ask Questions

Provably Faster Algorithms for Bilevel Optimization and Applications to Meta-Learning


Oct 15, 2020
Kaiyi Ji, Junjie Yang, Yingbin Liang

* 30 pages, 14 figures, 3 tables 

  Access Paper or Ask Questions

Boosting One-Point Derivative-Free Online Optimization via Residual Feedback


Oct 14, 2020
Yan Zhang, Yi Zhou, Kaiyi Ji, Michael M. Zavlanos


  Access Paper or Ask Questions

Improving the Convergence Rate of One-Point Zeroth-Order Optimization using Residual Feedback


Jun 18, 2020
Yan Zhang, Yi Zhou, Kaiyi Ji, Michael M. Zavlanos


  Access Paper or Ask Questions

Convergence of Meta-Learning with Task-Specific Adaptation over Partial Parameters


Jun 16, 2020
Kaiyi Ji, Jason D. Lee, Yingbin Liang, H. Vincent Poor

* 28 pages, 8 figures, 2 tables 

  Access Paper or Ask Questions

Proximal Gradient Algorithm with Momentum and Flexible Parameter Restart for Nonconvex Optimization


Feb 26, 2020
Yi Zhou, Zhe Wang, Kaiyi Ji, Yingbin Liang, Vahid Tarokh


  Access Paper or Ask Questions

Multi-Step Model-Agnostic Meta-Learning: Convergence and Improved Algorithms


Feb 20, 2020
Kaiyi Ji, Junjie Yang, Yingbin Liang

* 67 pages, 8 figures 

  Access Paper or Ask Questions

Robust Stochastic Bandit Algorithms under Probabilistic Unbounded Adversarial Attack


Feb 17, 2020
Ziwei Guan, Kaiyi Ji, Donald J Bucci Jr, Timothy Y Hu, Joseph Palombo, Michael Liston, Yingbin Liang

* Published at AAAI'20 

  Access Paper or Ask Questions

Improved Zeroth-Order Variance Reduced Algorithms and Analysis for Nonconvex Optimization


Oct 27, 2019
Kaiyi Ji, Zhe Wang, Yi Zhou, Yingbin Liang

* Published in ICML 2019 

  Access Paper or Ask Questions

Faster Stochastic Algorithms via History-Gradient Aided Batch Size Adaptation


Oct 21, 2019
Kaiyi Ji, Zhe Wang, Yi Zhou, Yingbin Liang


  Access Paper or Ask Questions

Momentum Schemes with Stochastic Variance Reduction for Nonconvex Composite Optimization


Feb 11, 2019
Yi Zhou, Zhe Wang, Kaiyi Ji, Yingbin Liang, Vahid Tarokh


  Access Paper or Ask Questions

Minimax Estimation of Neural Net Distance


Nov 02, 2018
Kaiyi Ji, Yingbin Liang

* To appear in Proc. NIPS 2018 

  Access Paper or Ask Questions

SpiderBoost: A Class of Faster Variance-reduced Algorithms for Nonconvex Optimization


Oct 25, 2018
Zhe Wang, Kaiyi Ji, Yi Zhou, Yingbin Liang, Vahid Tarokh


  Access Paper or Ask Questions

When Will Gradient Methods Converge to Max-margin Classifier under ReLU Models?


Oct 15, 2018
Tengyu Xu, Yi Zhou, Kaiyi Ji, Yingbin Liang


  Access Paper or Ask Questions

Learning Latent Features with Pairwise Penalties in Matrix Completion


Feb 16, 2018
Kaiyi Ji, Jian Tan, Yuejie Chi, Jinfeng Xu

* 31 pages, 8 figures 

  Access Paper or Ask Questions