AI Chat AI Image Generator AI Video Text to Speech

Regret Analysis of the Anytime Optimally Confident UCB Algorithm

03/29/2016

∙

by Tor Lattimore, et al.

∙

∙

I introduce and analyse an anytime version of the Optimally Confident UCB (OCUCB) algorithm designed for minimising the cumulative regret in finite-armed stochastic bandits with subgaussian noise. The new algorithm is simple, intuitive (in hindsight) and comes with the strongest finite-time regret guarantees for a horizon-free algorithm so far. I also show a finite-time lower bound that nearly matches the upper bound.

page 1

page 2

page 3

page 4

research

∙ 03/30/2019

Nearly Minimax-Optimal Regret for Linearly Parameterized Bandits

We study the linear contextual bandit problem with finite action sets. W...

0 Yingkai Li, et al. ∙

research

∙ 11/18/2015

Regret Analysis of the Finite-Horizon Gittins Index Strategy for Multi-Armed Bandits

I analyse the frequentist regret of the famous Gittins index strategy fo...

0 Tor Lattimore, et al. ∙

research

∙ 05/24/2019

Polynomial Cost of Adaptation for X -Armed Bandits

In the context of stochastic continuum-armed bandits, we present an algo...

0 Hédi Hadiji, et al. ∙

research

∙ 04/10/2019

Testing Unateness Nearly Optimally

We present an Õ(n^2/3/ϵ^2)-query algorithm that tests whether an unknown...

0 Xi Chen, et al. ∙

research

∙ 10/25/2018

Almost Optimal Algorithms for Linear Stochastic Bandits with Heavy-Tailed Payoffs

In linear stochastic bandits, it is commonly assumed that payoffs are wi...

0 Han Shao, et al. ∙

research

∙ 10/11/2022

Regret Analysis of the Stochastic Direct Search Method for Blind Resource Allocation

Motivated by programmatic advertising optimization, we consider the task...

0 Juliette Achddou, et al. ∙

research

∙ 04/28/2020

Nearly Optimal Regret for Stochastic Linear Bandits with Heavy-Tailed Payoffs

In this paper, we study the problem of stochastic linear bandits with fi...

5 Bo Xue, et al. ∙