Optimistic Online Convex Optimization in Dynamic Environments
This work addresses the need for adaptive algorithms in online optimization for dynamic settings, though it appears incremental as it builds on existing methods like Ader.
The paper tackles the problem of optimistic online convex optimization in dynamic environments by proposing ONES-OGP, an environment-adaptive algorithm that replaces components in Ader with optimistic variants and introduces adaptive tricks, achieving dynamic regret bounds that depend on characteristic terms instead of the number of rounds T.
In this paper, we study the optimistic online convex optimization problem in dynamic environments. Existing works have shown that Ader enjoys an $O\left(\sqrt{\left(1+P_T\right)T}\right)$ dynamic regret upper bound, where $T$ is the number of rounds, and $P_T$ is the path length of the reference strategy sequence. However, Ader is not environment-adaptive. Based on the fact that optimism provides a framework for implementing environment-adaptive, we replace Greedy Projection (GP) and Normalized Exponentiated Subgradient (NES) in Ader with Optimistic-GP and Optimistic-NES respectively, and name the corresponding algorithm ONES-OGP. We also extend the doubling trick to the adaptive trick, and introduce three characteristic terms naturally arise from optimism, namely $M_T$, $\widetilde{M}_T$ and $V_T+1_{L^2ρ\left(ρ+2 P_T\right)\leqslant\varrho^2 V_T}D_T$, to replace the dependence of the dynamic regret upper bound on $T$. We elaborate ONES-OGP with adaptive trick and its subgradient variation version, all of which are environment-adaptive.