Regret Bounds without Lipschitz Continuity: Online Learning with Relative-Lipschitz Losses

10/22/2020
by   Yihan Zhou, et al.
0

In online convex optimization (OCO), Lipschitz continuity of the functions is commonly assumed in order to obtain sublinear regret. Moreover, many algorithms have only logarithmic regret when these functions are also strongly convex. Recently, researchers from convex optimization proposed the notions of "relative Lipschitz continuity" and "relative strong convexity". Both of the notions are generalizations of their classical counterparts. It has been shown that subgradient methods in the relative setting have performance analogous to their performance in the classical setting. In this work, we consider OCO for relative Lipschitz and relative strongly convex functions. We extend the known regret bounds for classical OCO algorithms to the relative setting. Specifically, we show regret bounds for the follow the regularized leader algorithms and a variant of online mirror descent. Due to the generality of these methods, these results yield regret bounds for a wide variety of OCO algorithms. Furthermore, we further extend the results to algorithms with extra regularization such as regularized dual averaging.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/25/2022

Dynamic Regret of Online Mirror Descent for Relatively Smooth Convex Cost Functions

The performance of online convex optimization algorithms in a dynamic en...
research
05/23/2023

Data-Dependent Bounds for Online Portfolio Selection Without Lipschitzness and Smoothness

This work introduces the first small-loss and gradual-variation regret b...
research
02/09/2023

Optimistic Online Mirror Descent for Bridging Stochastic and Adversarial Online Convex Optimization

Stochastically Extended Adversarial (SEA) model is introduced by Sachs e...
research
07/22/2019

Online optimization of piecewise Lipschitz functions in changing environments

In an online optimization problem we are required to choose a sequence o...
research
09/08/2017

A Modular Analysis of Adaptive (Non-)Convex Optimization: Optimism, Composite Objectives, and Variational Bounds

Recently, much work has been done on extending the scope of online learn...
research
04/07/2016

Online Optimization of Smoothed Piecewise Constant Functions

We study online optimization of smoothed piecewise constant functions ov...
research
12/22/2021

A Unified Analysis Method for Online Optimization in Normed Vector Space

We present a unified analysis method that relies on the generalized cosi...

Please sign up or login with your details

Forgot password? Click here to reset