Online Optimization : Competing with Dynamic Comparators

01/26/2015
by   Ali Jadbabaie, et al.
0

Recent literature on online learning has focused on developing adaptive algorithms that take advantage of a regularity of the sequence of observations, yet retain worst-case performance guarantees. A complementary direction is to develop prediction methods that perform well against complex benchmarks. In this paper, we address these two directions together. We present a fully adaptive method that competes with dynamic benchmarks in which regret guarantee scales with regularity of the sequence of cost functions and comparators. Notably, the regret bound adapts to the smaller complexity measure in the problem environment. Finally, we apply our results to drifting zero-sum, two-player games where both players achieve no regret guarantees against best sequences of actions in hindsight.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/18/2012

Online Learning with Predictable Sequences

We present methods for online linear optimization that take advantage of...
research
10/25/2018

Adaptive Online Learning in Dynamic Environments

In this paper, we study online convex optimization in dynamic environmen...
research
02/06/2020

Minimizing Dynamic Regret and Adaptive Regret Simultaneously

Regret minimization is treated as the golden rule in the traditional stu...
research
02/15/2023

Improved Online Conformal Prediction via Strongly Adaptive Online Learning

We study the problem of uncertainty quantification via prediction sets, ...
research
01/31/2023

Unconstrained Dynamic Regret via Sparse Coding

Motivated by time series forecasting, we study Online Linear Optimizatio...
research
01/18/2023

Optimistic Dynamic Regret Bounds

Online Learning (OL) algorithms have originally been developed to guaran...
research
12/06/2022

Regret Minimization with Dynamic Benchmarks in Repeated Games

In repeated games, strategies are often evaluated by their ability to gu...

Please sign up or login with your details

Forgot password? Click here to reset