Non-stationary Projection-free Online Learning with Dynamic and Adaptive Regret Guarantees

by   Yibo Wang, et al.

Projection-free online learning has drawn increasing interest due to its efficiency in solving high-dimensional problems with complicated constraints. However, most existing projection-free online methods focus on minimizing the static regret, which unfortunately fails to capture the challenge of changing environments. In this paper, we investigate non-stationary projection-free online learning, and choose dynamic regret and adaptive regret to measure the performance. Specifically, we first provide a novel dynamic regret analysis for an existing projection-free method named BOGD_IP, and establish an 𝒊(T^3/4(1+P_T)) dynamic regret bound, where P_T denotes the path-length of the comparator sequence. Then, we improve the upper bound to 𝒊(T^3/4(1+P_T)^1/4) by running multiple BOGD_IP algorithms with different step sizes in parallel, and tracking the best one on the fly. Our results are the first general-case dynamic regret bounds for projection-free online learning, and can recover the existing 𝒊(T^3/4) static regret by setting P_T = 0. Furthermore, we propose a projection-free method to attain an 𝒊Ėƒ(τ^3/4) adaptive regret bound for any interval with length τ, which nearly matches the static regret over that interval. The essential idea is to maintain a set of BOGD_IP algorithms dynamically, and combine them by a meta algorithm. Moreover, we demonstrate that it is also equipped with an 𝒊(T^3/4(1+P_T)^1/4) dynamic regret bound. Finally, empirical studies verify our theoretical findings.


page 1

page 2

page 3

page 4

∙ 09/16/2023

Efficient Methods for Non-stationary Online Learning

Non-stationary online learning has drawn much attention in recent years....
∙ 01/31/2023

Online Learning in Dynamically Changing Environments

We study the problem of online learning and online regret minimization w...
∙ 10/09/2019

Derivative-Free Order-Robust Optimisation

In this paper, we formalise order-robust optimisation as an instance of ...
∙ 09/05/2019

More Adaptive Algorithms for Tracking the Best Expert

In this paper, we consider the problem of prediction with expert advice ...
∙ 03/01/2013

Second-Order Non-Stationary Online Learning for Regression

The goal of a learner, in standard online learning, is to have the cumul...
∙ 09/06/2019

Trading-Off Static and Dynamic Regret in Online Least-Squares and Beyond

Recursive least-squares algorithms often use forgetting factors as a heu...
∙ 11/06/2017

Online Learning for Changing Environments using Coin Betting

A key challenge in online learning is that classical algorithms can be s...

Please sign up or login with your details

Forgot password? Click here to reset