arXiv research

Optimal best-arm identification with known number of optimal arms.

New algorithms minimize regret with multiple best arms in large action spaces.

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

We study a generalization of the multi-armed bandit problem with multiple plays where there is a cost associated with pulling each arm and the agent has a budget at each time that dictates how much she can expect to spend. We derive an asymptotic regret lower bound for any uniformly efficient algorithm in our setting. …

Improved FTRL algorithm for multi-armed bandits with various regularizers and multiple optimal arms.

Simple greedy algorithms can excel in multi-objective bandits with multiple good arms.

We introduce in this paper a new algorithm for Multi-Armed Bandit (MAB) problems. A machine learning paradigm popular within Cognitive Network related topics (e.g., Spectrum Sensing and Allocation). We focus on the case where the rewards are exponentially distributed, which is common when dealing with Rayleigh fading c…

We discuss a multiple-play multi-armed bandit (MAB) problem in which several arms are selected at each round. Recently, Thompson sampling (TS), a randomized algorithm with a Bayesian spirit, has attracted much attention for its empirically excellent performance, and it is revealed to have an optimal regret bound in the…

As the cornerstone of modern portfolio theory, Markowitz's mean-variance optimization is considered a major model adopted in portfolio management. However, due to the difficulty of estimating its parameters, it cannot be applied to all periods. In some cases, naive strategies such as Equally-weighted and Value-weighted…

New algorithm eliminates arms to minimize regret in complex bandit problems.

Study optimal adaptive allocation for multi-armed bandits with Markovian rewards.

New strategy optimally identifies best arm in unknown variance Gaussian bandits.

Paper tackles best mixed arm identification with cost constraints in bandit models.

We consider a stochastic bandit problem with infinitely many arms. In this setting, the learner has no chance of trying all the arms even once and has to dedicate its limited number of samples only to a certain number of arms. All previous algorithms for this setting were designed for minimizing the cumulative regret o…

Proposes DEXP3.M for unknown delay in multi-arm bandit with multiple play.

Optimal strategy identified for minimizing regret in fixed-budget best arm selection.

Algorithm identifies Pareto front using multiple context directions and reuses exploration samples.

We consider the stochastic linear (multi-armed) contextual bandit problem with the possibility of hidden simple multi-armed bandit structure in which the rewards are independent of the contextual information. Algorithms that are designed solely for one of the regimes are known to be sub-optimal for the alternate regime…

New algorithm finds best feasible arm in grouped bandits.

Algorithm optimizes a single attribute in multi-armed bandits with constraints.

A new federated bandit problem with multiple adversaries, solved with a near-optimal algorithm.

Paper proposes Adaptive Pareto Exploration for identifying Pareto optimal arms in multi-objective scenarios.

We consider the problem of best arm identification in a variant of multi-armed bandits called linked bandits. In a single interaction with linked bandits, multiple arms are played sequentially until one of them receives a positive reward. Since each interaction provides feedback about more than one arm, the sample comp…

We consider network sparsification as an $L_0$-norm regularized binary optimization problem, where each unit of a neural network (e.g., weight, neuron, or channel, etc.) is attached with a stochastic binary gate, whose parameters are jointly optimized with original network parameters. The Augment-Reinforce-Merge (ARM),…

New algorithms improve performance guarantees for multi-armed bandits problems.

Optimal resource allocation in censored semi-bandits with unknown thresholds.

We investigate the adversarial bandit problem with multiple plays under semi-bandit feedback. We introduce a highly efficient algorithm that asymptotically achieves the performance of the best switching $m$-arm strategy with minimax optimal regret bounds. To construct our algorithm, we introduce a new expert advice alg…

We study the problem of identifying the top $m$ arms in a multi-armed bandit game. Our proposed solution relies on a new algorithm based on successive rejects of the seemingly bad arms, and successive accepts of the good ones. This algorithmic contribution allows to tackle other multiple identifications settings that w…

This work explores the idea of a causal contextual multi-armed bandit approach to automated marketing, where we estimate and optimize the causal (incremental) effects. Focusing on causal effect leads to better return on investment (ROI) by targeting only the persuadable customers who wouldn't have taken the action orga…

Many real-world functions are defined over both categorical and category-specific continuous variables and thus cannot be optimized by traditional Bayesian optimization (BO) methods. To optimize such functions, we propose a new method that formulates the problem as a multi-armed bandit problem, wherein each category co…

AGG-UCB uses neural networks to optimize group behaviors in contextual bandits.

TRIPLE efficiently optimizes prompts with a budget constraint.

LinFACT identifies all ε-best arms in linear bandits with near-optimal efficiency.

To backpropagate the gradients through stochastic binary layers, we propose the augment-REINFORCE-merge (ARM) estimator that is unbiased, exhibits low variance, and has low computational complexity. Exploiting variable augmentation, REINFORCE, and reparameterization, the ARM estimator achieves adaptive variance reducti…

Optimal policy for multi-armed multi-action bandits with unknown parameters.

Unified framework controls false discovery rate in bandit multiple testing.

The paper tackles multi-armed bandits with vector losses, focusing on minimizing the $\ell^\infty$-norm of relative losses.

In this paper, we study censored Semi-Bandits, a novel variant of the semi-bandits problem. The learner is assumed to have a fixed amount of resources, which it allocates to the arms at each time step. The loss observed from an arm is random and depends on the amount of resources allocated to it. More specifically, the…

No communication allows optimal instance-dependent regret guarantees in multi-player bandits.

Optimized Sharpe Ratio for better risk-adjusted decision-making in multi-armed bandits.

In this paper we propose the multi-objective contextual bandit problem with similarity information. This problem extends the classical contextual bandit problem with similarity information by introducing multiple and possibly conflicting objectives. Since the best arm in each objective can be different given the contex…

Optimal algorithm for high-dimensional stochastic linear bandits with sparse parameters.

FPML algorithm reduces regret by limiting the number of arms chosen per round.

New algorithm optimizes multi-armed bandit performance in stochastic and adversarial settings.

Optimal algorithm for latent bandits with cluster structure reduces regret to nearly optimal.

New algorithm tackles resource allocation in multi-armed bandits to balance speed and throughput.

A new algorithm for cryo-EM data collection that balances reward and latency.

A novel algorithm reduces communication costs in federated best arm identification.