arXiv research

The paper honors Lai's contributions to multi-armed bandits and establishes new regret bounds.

Upper and lower bounds on regret for noisy optimization of Brownian motion.

New bounds for Bayesian bandits show prior improves performance.

New algorithms identify best policies in discounted linear MDPs efficiently.

A bandit problem with filtered Poisson process data.

This paper is devoted to regret lower bounds in the classical model of stochastic multi-armed bandit. A well-known result of Lai and Robbins, which has then been extended by Burnetas and Katehakis, has established the presence of a logarithmic bound for all consistent policies. We relax the notion of consistence, and e…

Upper bound on withdrawal success for geometric Levy alpha-stable wealth process.

GP-UCB performs suboptimally under certain conditions, as shown by a new regret lower bound.

Study optimizes dynamic product selection and pricing using censored preference feedback.

BILBO optimizes bilevel problems without repeated lower-level optimizations.

Algorithm aggregates rewards from multiple players to learn related tasks in online bandit learning.

A new algorithm for better decision-making in recommendation systems.

This paper analyzes regret bounds for Gaussian process Thompson sampling.

The study analyzes batched methods for early stopping in stochastic multi-armed bandits.

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 hori…

New algorithm optimizes online decision-making with dynamically generated actions.

For an autonomous agent, executing a poor policy may be costly or even dangerous. For such agents, it is desirable to determine confidence interval lower bounds on the performance of any given policy without executing said policy. Current methods for exact high confidence off-policy evaluation that use importance sampl…

We study an original problem of pure exploration in a strategic bandit model motivated by Monte Carlo Tree Search. It consists in identifying the best action in a game, when the player may sample random outcomes of sequentially chosen pairs of actions. We propose two strategies for the fixed-confidence setting: Maximin…

New algorithm reduces regret in linear mixture SSPs without cost bounds.

Prove non-asymptotic bounds for minimal risk in statistical learning

A new federated multi-armed bandit framework with personalization balances generalization and personalization.

Paper presents robust confidence sequences for means with known moment bounds and arbitrary corruption.

Contextual bandits are widely used in Internet services from news recommendation to advertising, and to Web search. Generalized linear models (logistical regression in particular) have demonstrated stronger performance than linear models in many applications where rewards are binary. However, most theoretical analyses …

New algorithm minimizes Bayesian regret in offline linear bandits.

New algorithms tackle latent bandit problems with lower regret.

Specialists outperform generalists in ensemble classification.

Near-optimal per-action regret bounds for sleeping bandits are derived.

Paper improves regret bounds for Gaussian process upper confidence bound in Bayesian optimization.

The paper studies privacy-protected BAI with fixed confidence, deriving lower bounds and proposing an adaptive algorithm.

We consider the problem of near-optimal arm identification in the fixed confidence setting of the infinitely armed bandit problem when nothing is known about the arm reservoir distribution. We (1) introduce a PAC-like framework within which to derive and cast results; (2) derive a sample complexity lower bound for near…

Bayes-UCBVI tackles reinforcement learning with a new upper confidence bound method.

We study the linear contextual bandit problem with finite action sets. When the problem dimension is $d$, the time horizon is $T$, and there are $n \leq 2^{d/2}$ candidate actions per time period, we (1) show that the minimax expected regret is $Ω(\sqrt{dT (\log T) (\log n)})$ for every algorithm, and (2) introduce a V…

We consider the problem of \textit{best arm identification} with a \textit{fixed budget $T$}, in the $K$-armed stochastic bandit setting, with arms distribution defined on $[0,1]$. We prove that any bandit strategy, for at least one bandit problem characterized by a complexity $H$, will misidentify the best arm with pr…

This paper studies the problem of finding the exact ranking from noisy comparisons. A comparison over a set of $m$ items produces a noisy outcome about the most preferred item, and reveals some information about the ranking. By repeatedly and adaptively choosing items to compare, we want to fully rank the items with a …

A new differentiable UCB algorithm for linear bandits learns adaptive confidence bounds.

The estimation of probabilities of default (PDs) for low default portfolios by means of upper confidence bounds is a well established procedure in many financial institutions. However, there are often discussions within the institutions or between institutions and supervisors about which confidence level to use for the…

New algorithm for multi-fidelity bandits reduces costs and improves regret.

This paper improves GP-UCB by using a shifted exponential distribution for confidence parameters.

CascadeBAI identifies best arms in cascading bandits with fixed confidence.

Deep learning method for pricing and hedging American-style options.

This note gives a short, self-contained, proof of a sharp connection between Gittins indices and Bayesian upper confidence bound algorithms. I consider a Gaussian multi-armed bandit problem with discount factor $γ$. The Gittins index of an arm is shown to equal the $γ$-quantile of the posterior distribution of the arm'…

Improved Bayesian optimisation method using randomised Gaussian process UCB.

The paper proposes a novel upper confidence bound (UCB) procedure for identifying the arm with the largest mean in a multi-armed bandit game in the fixed confidence setting using a small number of total samples. The procedure cannot be improved in the sense that the number of samples required to identify the best arm i…

Optimal simple regret bound for Gaussian Process bandits.

Estimation of individual treatment effects is commonly used as the basis for contextual decision making in fields such as healthcare, education, and economics. However, it is often sufficient for the decision maker to have estimates of upper and lower bounds on the potential outcomes of decision alternatives to assess …

Bayesian methods improve drug discovery experiment design.

Optimal strategy for reinforcement learning with delayed observations.

One-bit feedback suffices for a bandit problem's optimal strategy.