Optimistic Online Convex Optimization in Dynamic Environments
share
In this paper, we study the optimistic online convex optimization problem in dynamic environments. Existing works have shown that Ader enjoys an O(√((1+P_T)T)) 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, M_T and V_T+1_L^2ρ(ρ+2 P_T)⩽ϱ^2 V_TD_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.
READ FULL TEXT