Optimal Dynamic Regret in Proper Online Learning with Strongly Convex Losses and Beyond

01/21/2022
by   Dheeraj Baby, et al.
0

We study the framework of universal dynamic regret minimization with strongly convex losses. We answer an open problem in Baby and Wang 2021 by showing that in a proper learning setup, Strongly Adaptive algorithms can achieve the near optimal dynamic regret of Õ(d^1/3 n^1/3TV[u_1:n]^2/3∨ d) against any comparator sequence u_1,…,u_n simultaneously, where n is the time horizon and TV[u_1:n] is the Total Variation of comparator. These results are facilitated by exploiting a number of new structures imposed by the KKT conditions that were not considered in Baby and Wang 2021 which also lead to other improvements over their results such as: (a) handling non-smooth losses and (b) improving the dimension dependence on regret. Further, we also derive near optimal dynamic regret rates for the special case of proper online learning with exp-concave losses and an L_∞ constrained decision set.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/23/2021

Optimal Dynamic Regret in Exp-Concave Online Learning

We consider the problem of the Zinkevich (2003)-style dynamic regret min...
research
05/04/2022

Second Order Path Variationals in Non-Stationary Online Learning

We consider the problem of universal dynamic regret minimization under e...
research
11/22/2021

Dynamic Regret for Strongly Adaptive Methods and Optimality of Online KRR

We consider the framework of non-stationary Online Convex Optimization w...
research
08/29/2022

Online Bidding Algorithms for Return-on-Spend Constrained Advertisers

Online advertising has recently grown into a highly competitive and comp...
research
03/16/2016

Regret Minimization in Repeated Games: A Set-Valued Dynamic Programming Approach

The regret-minimization paradigm has emerged as an effective technique f...
research
01/23/2021

An Optimal Reduction of TV-Denoising to Adaptive Online Learning

We consider the problem of estimating a function from n noisy samples wh...
research
09/28/2021

Near-Linear Time Algorithm with Near-Logarithmic Regret Per Switch for Mixable/Exp-Concave Losses

We investigate the problem of online learning, which has gained signific...

Please sign up or login with your details

Forgot password? Click here to reset