activity
20172020
most citedImproved Zeroth-Order Variance Reduced Algorithms and Analysis for Nonconvex Optimization

16 citations · 28 across the 5 of their papers we have counts for

collaborators

9 papers

cs.LG20201 cited

Robust Stochastic Bandit Algorithms under Probabilistic Unbounded Adversarial Attack

Ziwei Guan, Kaiyi Ji, Donald J Bucci +4

The multi-armed bandit formalism has been extensively studied under various attack models, in which an adversary can modify the reward revealed to the player. Previous studies focu…

math.OC2020

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

Yi Zhou, Zhe Wang, Kaiyi Ji +2

Various types of parameter restart schemes have been proposed for accelerated gradient algorithms to facilitate their practical convergence in convex optimization. However, the con…

cs.LG2020

Theoretical Convergence of Multi-Step Model-Agnostic Meta-Learning

Kaiyi Ji, Junjie Yang, Yingbin Liang

As a popular meta-learning approach, the model-agnostic meta-learning (MAML) algorithm has been widely used due to its simplicity and effectiveness. However, the convergence of the…

cs.LG201916 cited

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

Kaiyi Ji, Zhe Wang, Yi Zhou +1

Two types of zeroth-order stochastic algorithms have recently been designed for nonconvex optimization respectively based on the first-order techniques SVRG and SARAH/SPIDER. This…

math.OC2019

History-Gradient Aided Batch Size Adaptation for Variance Reduced Algorithms

Kaiyi Ji, Zhe Wang, Bowen Weng +3

Variance-reduced algorithms, although achieve great theoretical performance, can run slowly in practice due to the periodic gradient estimation with a large batch of data. Batch-si…

math.OC201911 cited

Momentum Schemes with Stochastic Variance Reduction for Nonconvex Composite Optimization

Yi Zhou, Zhe Wang, Kaiyi Ji +2

Two new stochastic variance-reduced algorithms named SARAH and SPIDER have been recently proposed, and SPIDER has been shown to achieve a near-optimal gradient oracle complexity fo…