Bandits for BMO Functions

07/17/2020 ∙ by Tianyu Wang, et al. ∙ 0 ∙ share

We study the bandit problem where the underlying expected reward is a Bounded Mean Oscillation (BMO) function. BMO functions are allowed to be discontinuous and unbounded, and are useful in modeling signals with infinities in the do-main. We develop a toolset for BMO bandits, and provide an algorithm that can achieve poly-log δ-regret – a regret measured against an arm that is optimal after removing a δ-sized portion of the arm space.

READ FULL TEXT

Nonparametric Contextual Bandits in an Unknown Metric Space

Consider a nonparametric contextual multi-arm bandit problem where each ...
08/03/2019 ∙ by Nirandika Wanigasekara, et al. ∙ 6 ∙ share

read it
Thompson Sampling for CVaR Bandits

Risk awareness is an important feature to formulate a variety of real wo...
12/10/2020 ∙ by Dorian Baudry, et al. ∙ 0 ∙ share

read it
Recovering Bandits

We study the recovering bandits problem, a variant of the stochastic mul...
10/31/2019 ∙ by Ciara Pike-Burke, et al. ∙ 0 ∙ share

read it
Compliance-Aware Bandits

Motivated by clinical trials, we study bandits with observable non-compl...
02/09/2016 ∙ by Nicolás Della Penna, et al. ∙ 0 ∙ share

read it
The Combinatorial Multi-Bandit Problem and its Application to Energy Management

We study a Combinatorial Multi-Bandit Problem motivated by applications ...
10/30/2020 ∙ by Tobias Jacobs, et al. ∙ 0 ∙ share

read it
Efficient and Robust Algorithms for Adversarial Linear Contextual Bandits

We consider an adversarial variant of the classic K-armed linear context...
02/01/2020 ∙ by Gergely Neu, et al. ∙ 0 ∙ share

read it
Predictive Bandits

We introduce and study a new class of stochastic bandit problems, referr...
04/02/2020 ∙ by Simon Lindståhl, et al. ∙ 0 ∙ share

read it

Bandits for BMO Functions

Authors

Nonparametric Contextual Bandits in an Unknown Metric Space

Thompson Sampling for CVaR Bandits

Recovering Bandits

Compliance-Aware Bandits

The Combinatorial Multi-Bandit Problem and its Application to Energy Management

Efficient and Robust Algorithms for Adversarial Linear Contextual Bandits

Predictive Bandits

This week in AI