Adaptivity and Non-stationarity: Problem-dependent Dynamic Regret for Online Convex Optimization

12/29/2021
by   Peng Zhao, et al.
7

We investigate online convex optimization in non-stationary environments and choose the dynamic regret as the performance measure, defined as the difference between cumulative loss incurred by the online algorithm and that of any feasible comparator sequence. Let T be the time horizon and P_T be the path-length that essentially reflects the non-stationarity of environments, the state-of-the-art dynamic regret is 𝒪(√(T(1+P_T))). Although this bound is proved to be minimax optimal for convex functions, in this paper, we demonstrate that it is possible to further enhance the guarantee for some easy problem instances, particularly when online functions are smooth. Specifically, we propose novel online algorithms that can leverage smoothness and replace the dependence on T in the dynamic regret by problem-dependent quantities: the variation in gradients of loss functions, the cumulative loss of the comparator sequence, and the minimum of the previous two terms. These quantities are at most 𝒪(T) while could be much smaller in benign environments. Therefore, our results are adaptive to the intrinsic difficulty of the problem, since the bounds are tighter than existing results for easy problems and meanwhile guarantee the same rate in the worst case. Notably, our algorithm requires only one gradient per iteration, which shares the same gradient query complexity with the methods developed for optimizing the static regret. As a further application, we extend the results from the full-information setting to bandit convex optimization with two-point feedback and thereby attain the first problem-dependent dynamic regret for such bandit tasks.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/07/2020

Dynamic Regret of Convex and Smooth Functions

We investigate online convex optimization in non-stationary environments...
research
07/29/2019

Bandit Convex Optimization in Non-stationary Environments

Bandit Convex Optimization (BCO) is a fundamental framework for modeling...
research
05/16/2016

Tracking Slowly Moving Clairvoyant: Optimal Dynamic Regret of Online Learning with True and Noisy Gradient

This work focuses on dynamic regret of online convex optimization that c...
research
05/20/2023

Non-stationary Online Convex Optimization with Arbitrary Delays

Online convex optimization (OCO) with arbitrary delays, in which gradien...
research
03/28/2022

Optimistic Online Convex Optimization in Dynamic Environments

In this paper, we study the optimistic online convex optimization proble...
research
06/30/2019

Efficient Online Convex Optimization with Adaptively Minimax Optimal Dynamic Regret

We introduce an online convex optimization algorithm using projected sub...
research
07/17/2023

Universal Online Learning with Gradual Variations: A Multi-layer Online Ensemble Approach

In this paper, we propose an online convex optimization method with two ...

Please sign up or login with your details

Forgot password? Click here to reset