Efficient Projection-Free Online Methods with Stochastic Recursive Gradient (original) (raw)

Authors

• Jiahao Xie Zhejiang University
• Zebang Shen University of Pennsylvania
• Chao Zhang Zhejiang University
• Boyu Wang University of Western Ontario
• Hui Qian Zhejiang University

DOI:

https://doi.org/10.1609/aaai.v34i04.6116

Abstract

This paper focuses on projection-free methods for solving smooth Online Convex Optimization (OCO) problems. Existing projection-free methods either achieve suboptimal regret bounds or have high per-round computational costs. To fill this gap, two efficient projection-free online methods called ORGFW and MORGFW are proposed for solving stochastic and adversarial OCO problems, respectively. By employing a recursive gradient estimator, our methods achieve optimal regret bounds (up to a logarithmic factor) while possessing low per-round computational costs. Experimental results demonstrate the efficiency of the proposed methods compared to state-of-the-arts.

How to Cite

Xie, J., Shen, Z., Zhang, C., Wang, B., & Qian, H. (2020). Efficient Projection-Free Online Methods with Stochastic Recursive Gradient. Proceedings of the AAAI Conference on Artificial Intelligence, 34(04), 6446-6453. https://doi.org/10.1609/aaai.v34i04.6116

Issue

Section

AAAI Technical Track: Machine Learning