Adaptive Online Learning in Dynamic Environments

10/25/2018
by   Moshe Y. Vardi, et al.
0

In this paper, we study online convex optimization in dynamic environments, and aim to bound the dynamic regret with respect to any sequence of comparators. Existing work have shown that online gradient descent enjoys an O(√(T)(1+P_T)) dynamic regret, where T is the number of iterations and P_T is the path-length of the comparator sequence. However, this result is unsatisfactory, as there exists a large gap from the Ω(√(T(1+P_T))) lower bound established in our paper. To address this limitation, we develop a novel online method, namely adaptive learning for dynamic environment (Ader), which achieves an optimal O(√(T(1+P_T))) dynamic regret. The basic idea is to maintain a set of experts, each attaining an optimal dynamic regret for a specific path-length, and combines them with an expert-tracking algorithm. Furthermore, we propose an improved Ader based on the surrogate loss, and in this way the number of gradient evaluations per round is reduced from O( T) to 1. Finally, we extend Ader to the setting that a sequence of dynamical models is available to characterize the comparators.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/06/2020

Unconstrained Online Optimization: Dynamic Regret Analysis of Strongly Convex and Smooth Problems

The regret bound of dynamic online learning algorithms is often expresse...
research
03/28/2022

Optimistic Online Convex Optimization in Dynamic Environments

In this paper, we study the optimistic online convex optimization proble...
research
09/05/2019

More Adaptive Algorithms for Tracking the Best Expert

In this paper, we consider the problem of prediction with expert advice ...
research
01/07/2013

Dynamical Models and Tracking Regret in Online Convex Programming

This paper describes a new online convex optimization method which incor...
research
09/04/2022

Dynamic Regret of Adaptive Gradient Methods for Strongly Convex Problems

Adaptive gradient algorithms such as ADAGRAD and its variants have gaine...
research
01/26/2015

Online Optimization : Competing with Dynamic Comparators

Recent literature on online learning has focused on developing adaptive ...
research
01/31/2023

Unconstrained Dynamic Regret via Sparse Coding

Motivated by time series forecasting, we study Online Linear Optimizatio...

Please sign up or login with your details

Forgot password? Click here to reset