Dynamic Regret of Online Mirror Descent for Relatively Smooth Convex Cost Functions

TL;DR

This paper establishes bounds on the dynamic regret of online mirror descent algorithms for relatively smooth convex functions, extending analysis to cases lacking Lipschitz continuity or uniform smoothness, with practical implications.

Contribution

It introduces dynamic regret bounds for online mirror descent under relative smoothness and strong convexity, broadening applicability beyond traditional assumptions.

Findings

Dynamic regret bounds depend on path length and functional variation.

Additional bounds are derived under relatively strong convexity.

Numerical experiments show benefits of using relative smoothness in practice.

Abstract

The performance of online convex optimization algorithms in a dynamic environment is often expressed in terms of the dynamic regret, which measures the decision maker's performance against a sequence of time-varying comparators. In the analysis of the dynamic regret, prior works often assume Lipschitz continuity or uniform smoothness of the cost functions. However, there are many important cost functions in practice that do not satisfy these conditions. In such cases, prior analyses are not applicable and fail to guarantee the optimization performance. In this letter, we show that it is possible to bound the dynamic regret, even when neither Lipschitz continuity nor uniform smoothness is present. We adopt the notion of relative smoothness with respect to some user-defined regularization function, which is a much milder requirement on the cost functions. We first show that under relative smoothness, the dynamic regret has an upper bound based on the path length and functional variation. We then show that with an additional condition of relatively strong convexity, the dynamic regret can be bounded by the path length and gradient variation. These regret bounds provide performance guarantees to a wide variety of online optimization problems that arise in different application domains. Finally, we present numerical experiments that demonstrate the advantage of adopting a regularization function under which the cost functions are relatively smooth.