DeepAI AI Chat
Log In Sign Up

Adversaries in Online Learning Revisited: with applications in Robust Optimization and Adversarial training

by   Sebastian Pokutta, et al.
Alibaba Group
Zuse Institute Berlin

We revisit the concept of "adversary" in online learning, motivated by solving robust optimization and adversarial training using online learning methods. While one of the classical setups in online learning deals with the "adversarial" setup, it appears that this concept is used less rigorously, causing confusion in applying results and insights from online learning. Specifically, there are two fundamentally different types of adversaries, depending on whether the "adversary" is able to anticipate the exogenous randomness of the online learning algorithms. This is particularly relevant to robust optimization and adversarial training because the adversarial sequences are often anticipative, and many online learning algorithms do not achieve diminishing regret in such a case. We then apply this to solving robust optimization problems or (equivalently) adversarial training problems via online learning and establish a general approach for a large variety of problem classes using imaginary play. Here two players play against each other, the primal player playing the decisions and the dual player playing realizations of uncertain data. When the game terminates, the primal player has obtained an approximately robust solution. This meta-game allows for solving a large variety of robust optimization and multi-objective optimization problems and generalizes the approach of arXiv:1402.6361.


page 1

page 2

page 3

page 4


Continuous Online Learning and New Insights to Online Imitation Learning

Online learning is a powerful tool for analyzing iterative algorithms. H...

Approachability in unknown games: Online learning meets multi-objective optimization

In the standard setting of approachability there are two players and a t...

Playing the Game of Universal Adversarial Perturbations

We study the problem of learning classifiers robust to universal adversa...

Online Learning with Imperfect Hints

We consider a variant of the classical online linear optimization proble...

Online Learning and Solving Infinite Games with an ERM Oracle

While ERM suffices to attain near-optimal generalization error in the st...

Normalized Online Learning

We introduce online learning algorithms which are independent of feature...

Online Learning: Stochastic and Constrained Adversaries

Learning theory has largely focused on two main learning scenarios. The ...