Skip to yearly menu bar Skip to main content


Adaptive Regret of Convex and Smooth Functions

Lijun Zhang · Tie-Yan Liu · Zhi-Hua Zhou

Pacific Ballroom #161

Keywords: [ Online Learning ] [ Large Scale Learning and Big Data ] [ Convex Optimization ]


We investigate online convex optimization in changing environments, and choose the adaptive regret as the performance measure. The goal is to achieve a small regret over every interval so that the comparator is allowed to change over time. Different from previous works that only utilize the convexity condition, this paper further exploits smoothness to improve the adaptive regret. To this end, we develop novel adaptive algorithms for convex and smooth functions, and establish problem-dependent regret bounds over any interval. Our regret bounds are comparable to existing results in the worst case, and become much tighter when the comparator has a small loss.

Live content is unavailable. Log in and register to view live content