Accelerated Rates between Stochastic and Adversarial Online Convex Optimization

03/06/2023
by   Sarah Sachs, et al.
0

Stochastic and adversarial data are two widely studied settings in online learning. But many optimization tasks are neither i.i.d. nor fully adversarial, which makes it of fundamental interest to get a better theoretical understanding of the world between these extremes. In this work we establish novel regret bounds for online convex optimization in a setting that interpolates between stochastic i.i.d. and fully adversarial losses. By exploiting smoothness of the expected losses, these bounds replace a dependence on the maximum gradient length by the variance of the gradients, which was previously known only for linear losses. In addition, they weaken the i.i.d. assumption by allowing, for example, adversarially poisoned rounds, which were previously considered in the related expert and bandit settings. In the fully i.i.d. case, our regret bounds match the rates one would expect from results in stochastic acceleration, and we also recover the optimal stochastically accelerated rates via online-to-batch conversion. In the fully adversarial case our bounds gracefully deteriorate to match the minimax regret. We further provide lower bounds showing that our regret upper bounds are tight for all intermediate regimes in terms of the stochastic variance and the adversarial variation of the loss gradients.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/15/2022

Between Stochastic and Adversarial Online Convex Optimization: Improved Regret Bounds via Smoothness

Stochastic and adversarial data are two widely studied settings in onlin...
research
02/07/2021

Lazy OCO: Online Convex Optimization on a Switching Budget

We study a variant of online convex optimization where the player is per...
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
12/03/2020

Online learning with dynamics: A minimax perspective

We study the problem of online learning with dynamics, where a learner i...
research
05/20/2018

Transitions, Losses, and Re-parameterizations: Elements of Prediction Games

This thesis presents some geometric insights into three different types ...
research
02/24/2023

Best-of-Three-Worlds Linear Bandit Algorithm with Variance-Adaptive Regret Bounds

This paper proposes a linear bandit algorithm that is adaptive to enviro...
research
04/19/2019

Minimax Optimal Online Stochastic Learning for Sequences of Convex Functions under Sub-Gradient Observation Failures

We study online convex optimization under stochastic sub-gradient observ...

Please sign up or login with your details

Forgot password? Click here to reset