arXiv research

New algorithm improves materials discovery using max K-Armed Bandit.

This paper is devoted to the study of the max K-armed bandit problem, which consists in sequentially allocating resources in order to detect extreme values. Our contribution is twofold. We first significantly refine the analysis of the ExtremeHunter algorithm carried out in Carpentier and Valko (2014), and next propose…

We consider the Max $K$-Armed Bandit problem, where a learning agent is faced with several sources (arms) of items (rewards), and interested in finding the best item overall. At each time step the agent chooses an arm, and obtains a random real valued reward. The rewards of each arm are assumed to be i.i.d., with an un…

We consider the Max $K$-Armed Bandit problem, where a learning agent is faced with several stochastic arms, each a source of i.i.d. rewards of unknown distribution. At each time step the agent chooses an arm, and observes the reward of the obtained sample. Each sample is considered here as a separate item with the rewa…

New approach to multi-armed bandit problem aims to maximize highest total reward.

In the Best-$K$ identification problem (Best-$K$-Arm), we are given $N$ stochastic bandit arms with unknown reward distributions. Our goal is to identify the $K$ arms with the largest means with high confidence, by drawing samples from the arms adaptively. This problem is motivated by various practical applications and…

Motivated by models of human decision making proposed to explain commonly observed deviations from conventional expected value preferences, we formulate two stochastic multi-armed bandit problems with distorted probabilities on the reward distributions: the classic $K$-armed bandit and the linearly parameterized bandit…

New algorithm achieves near-optimal performance in dueling bandit problem.

In the Best-$k$-Arm problem, we are given $n$ stochastic bandit arms, each associated with an unknown reward distribution. We are required to identify the $k$ arms with the largest means by taking as few samples as possible. In this paper, we make progress towards a complete characterization of the instance-wise sample…

New trade-off found in bandit problems with unknown range.

New algorithm identifies optimal subtrees in fixed-budget tree search.

New algorithms for batched dueling bandits with improved regret bounds.

Study non-oblivious adversarial bandits with delayed feedback and propose algorithms with improved regret bounds.

A new approach to hedging using contextual bandit models outperforms traditional methods.

New algorithm reduces high-probability regret for time-varying feedback graphs.

Develops a framework for clustering and distribution matching with bandit feedback.

Study on policy gradient for stochastic bandits using diffusion approximation.

We consider two multi-armed bandit problems with $n$ arms: (i) given an $ε> 0$, identify an arm with mean that is within $ε$ of the largest mean and (ii) given a threshold $μ_0$ and integer $k$, identify $k$ arms with means larger than $μ_0$. Existing lower bounds and algorithms for the PAC framework suggest that both …

Short note on soft-max and policy gradients in bandit problems using Lyapunov functions.

Top-two algorithm improved for best-k-arm selection.

New bandit problem for finding best group of arms with worst mean reward.

We study the $K$-armed dueling bandit problem, a variation of the standard stochastic bandit problem where the feedback is limited to relative comparisons of a pair of arms. We introduce a tight asymptotic regret lower bound that is based on the information divergence. An algorithm that is inspired by the Deterministic…

Optimism stabilizes Thompson Sampling for adaptive inference in multi-armed bandits.

We analyze the $K$-armed bandit problem where the reward for each arm is a noisy realization based on an observed context under mild nonparametric assumptions. We attain tight results for top-arm identification and a sublinear regret of $\widetilde{O}\Big(T^{\frac{1+D}{2+D}}\Big)$, where $D$ is the context dimension, f…

Improved UCB algorithm for diversity in bandits with lower bounds.

Unified theory for UCB policies in total and max bandit problems.

This review examines bandit problems in AI using statistical methods.

We study the K-armed dueling bandit problem, a variation of the standard stochastic bandit problem where the feedback is limited to relative comparisons of a pair of arms. The hardness of recommending Copeland winners, the arms that beat the greatest number of other arms, is characterized by deriving an asymptotic regr…

Motivated by posted price auctions where buyers are grouped in an unknown number of latent types characterized by their private values for the good on sale, we investigate revenue maximization in stochastic dynamic pricing when the distribution of buyers' private values is supported on an unknown set of points in [0,1]…

The paper tackles non-stationary MAB with periodic rewards.

A collaborative algorithm reduces regret in federated linear contextual bandits.

A classic setting of the stochastic K-armed bandit problem is considered in this note. In this problem it has been known that KL-UCB policy achieves the asymptotically optimal regret bound and KL-UCB+ policy empirically performs better than the KL-UCB policy although the regret bound for the original form of the KL-UCB…

A new algorithm for selecting top-k arms in extreme contextual bandits with improved efficiency.

We consider the stochastic bandit problem in the sublinear space setting, where one cannot record the win-loss record for all $K$ arms. We give an algorithm using $O(1)$ words of space with regret \[ \sum_{i=1}^{K}\frac{1}{Δ_i}\log \frac{Δ_i}Δ\log T \] where $Δ_i$ is the gap between the best arm and arm $i$ and $Δ$ is …

New algorithms improve multi-task bandit performance by transferring reward samples.

A new algorithm reduces communication costs for collaborative decision-making across clients.

ODC protocol improves learning in asynchronous multi-agent bandits.

A new algorithm reduces regret in bandit problems with adversarial corruptions.

Improved algorithm for bandits with delayed feedback, combining adversarial and stochastic performance.

New method tackles high-dimensional contextual bandits with flexible kernel models.

Algorithm identifies Pareto front in multi-objective bandits efficiently.

Unified approach for non-stationary linear bandits with dynamic regret.

The paper tackles a bandit problem with infinitely many arms per group, aiming to identify the group with the highest quantile reward.

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…

The paper provides tight bounds for improving multi-armed bandits problem.

We propose $\tt RandUCB$, a bandit strategy that builds on theoretically derived confidence intervals similar to upper confidence bound (UCB) algorithms, but akin to Thompson sampling (TS), it uses randomization to trade off exploration and exploitation. In the $K$-armed bandit setting, we show that there are infinitel…

The information-theoretic analysis by Russo and Van Roy (2014) in combination with minimax duality has proved a powerful tool for the analysis of online learning algorithms in full and partial information settings. In most applications there is a tantalising similarity to the classical analysis based on mirror descent.…

An algorithm for maximizing rewards under linear cost constraints.