TY - JOUR
AU - Wan, Yuanyu
AU - Zhang, Lijun
PY - 2021/05/18
Y2 - 2024/04/20
TI - Projection-free Online Learning over Strongly Convex Sets
JF - Proceedings of the AAAI Conference on Artificial Intelligence
JA - AAAI
VL - 35
IS - 11
SE - AAAI Technical Track on Machine Learning IV
DO - 10.1609/aaai.v35i11.17209
UR - https://ojs.aaai.org/index.php/AAAI/article/view/17209
SP - 10076-10084
AB - To efficiently solve online problems with complicated constraints, projection-free algorithms including online frank-wolfe (OFW) and its variants have received significant interest recently. However, in the general case, existing efficient projection-free algorithms only achieved the regret bound of O(T^{3/4}), which is worse than the regret of projection-based algorithms, where T is the number of decision rounds. In this paper, we study the special case of online learning over strongly convex sets, for which we first prove that OFW can enjoy a better regret bound of O(T^{2/3}) for general convex losses. The key idea is to refine the decaying step-size in the original OFW by a simple line search rule. Furthermore, for strongly convex losses, we propose a strongly convex variant of OFW by redefining the surrogate loss function in OFW. We show that it achieves a regret bound of O(T^{2/3}) over general convex sets and a better regret bound of O(T^{1/2}) over strongly convex sets.
ER -