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. |
Year | Venue | DocType |
---|---|---|
2020 | THIRTY-FOURTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THE THIRTY-SECOND INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE AND THE TENTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE | Conference |
Volume | ISSN | Citations |
34 | 2159-5399 | 0 |
PageRank | References | Authors |
0.34 | 0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jiahao Xie | 1 | 0 | 2.03 |
Zebang Shen | 2 | 17 | 9.36 |
Chao Zhang | 3 | 8 | 5.49 |
Boyu Wang | 4 | 52 | 12.32 |
Hui Qian | 5 | 59 | 13.26 |