Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,181 papers · 148 categories

Trend · papers per month

3978117156 · Jun 202019922001200920182026
48 results for ε-good arm

New algorithm identifies good arms with fewer samples when thresholds are close.

problem Good arm identification in bandit problems with small threshold gaps.
method Proposes lil'HDoC algorithm to improve GAI under small threshold gaps.
result Sample complexity of first λ output arm is nearly identical to HDoC algorithm when thresholds are close.

This work optimizes identifying good arms in nonparametric multi-armed bandits.

problem Efficiently identifying arms with high means in nonparametric settings.
method Combining reward-maximizing sampling with a nonparametric sequential test for anytime-valid labeling.
result Achieves minimax optimal stopping times for identifying arms above a threshold.

The paper tackles infinite-armed bandits with general reservoirs, providing necessary and sufficient conditions for ε-good arm selection.

problem Characterizing conditions for selecting ε-good arms with high probability in infinite-armed bandits.
method The approach is based on successive halving with early discarding of arms after a single pull, analyzing the reservoir distribution without assuming its form.
result The algorithm provably returns an ε-good arm with high probability, explaining the effectiveness of Hyperband's aggressive bracketing.

New method for identifying best arm in batched multi-armed bandit problems.

problem Identifying the best arm in multi-armed bandit problems where arms are sampled in batches.
method General linear programming framework for best arm identification in batched multi-armed bandit problems.
result Demonstrated good performance in numerical studies compared to UCB-type or Thompson sampling methods.

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

problem Optimizing multiple objectives in bandits is traditionally harder.
method Introduced greedy algorithms that exploit multiple good arms for multiple objectives.
result Simple greedy algorithms achieve strong performance in multi-objective bandits.

New definitions and algorithms improve sample complexity for identifying good arms in multi-armed bandits.

problem Identifying arms with means close to the maximum or larger than a threshold.
method Formalized definitions, lower bounds, and practical algorithms.
result Achieved nearly matching upper bounds with sample complexities of Θ( rac{n}{m}) and Θ( rac{n}{m}k).

We study the problem of identifying the top mm 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…

2012-05-14abs ↗pdf ↗

We consider the problem of minimizing the regret in stochastic multi-armed bandit, when the measure of goodness of an arm is not the mean return, but some general function of the mean and the variance.We characterize the conditions under which learning is possible and present examples for which no natural algorithm can…

2014-05-05abs ↗pdf ↗

The paper tackles identifying multiple best arms in stochastic bandits, improving sample efficiency.

problem Identifying multiple best arms in stochastic multi-armed bandits.
method Developed a fully sequential PAC algorithm, GLUCB, and presented lower and upper bounds.
result Improved sample efficiency for identifying multiple best arms.

New algorithm improves online decision making by adaptively inferring arm rewards.

problem Adaptive selection of arms in MAB leads to non-iid data, complicating accurate inference.
method Proposes a doubly adaptive TS algorithm that leverages causal inference for adaptive reweighting.
result Demonstrates superior empirical performance in identifying the best arm compared to UCB and TS.

Improved knowledge gradient (iKG) outperforms the original KG algorithm in best arm identification problems.

problem Best arm identification (BAI) problem with limitations of the original KG algorithm.
method Follows the one-step look ahead of KG but chooses the measurement that maximizes the probability of selecting the best arm.
result Improved knowledge gradient (iKG) is asymptotically optimal and easier to extend to variant BAI problems.

Develops algorithms to exploit historical and pre-clustered arm information in bandit problems.

problem Optimizing decision-making in multi-armed bandit and contextual bandit problems with historical observations and pre-clustered arms.
method META algorithm that combines historical observations and pre-clustering information, deriving regret bounds for various scenarios.
result META algorithm effectively balances between using historical observations and clustering, outperforming the other in different scenarios.

Decentralized multi-armed bandits improve privacy in collaborative settings.

problem Privacy in collaborative multi-armed bandit exploration.
method Generic algorithm Decentralized Elimination using best arm identification algorithms.
result The algorithm insures privacy with low communication cost and sample complexity penalty.

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

problem Identifying Pareto optimal arms in multi-objective scenarios with relaxed constraints.
method Adaptive Pareto Exploration strategy for different relaxations of Pareto Set Identification.
result Reduction in sample complexity when identifying at most k Pareto optimal arms.

New algorithms solve complex function optimization problems.

problem Optimizing unknown functions in competitive learning models.
method Proposed F-LCB algorithm based on UCB-type methods for nonlinear optimization.
result Regret upper bounds for the F-LCB algorithm derived from base algorithms' convergence rates.

The paper emphasizes the importance of joint predictions over marginal predictions for decision-making.

problem The need for accurate joint predictions in decision-making problems.
method The paper analyzes combinatorial decision problems, sequential predictions, and multi-armed bandits, introducing an approximate Thompson sampling algorithm and new regret bounds.
result Accurate joint predictions are essential for good performance in decision-making problems.

We describe a novel algorithm for noisy global optimisation and continuum-armed bandits, with good convergence properties over any continuous reward function having finitely many polynomial maxima. Over such functions, our algorithm achieves square-root regret in bandits, and inverse-square-root error in optimisation, …

2013-02-11abs ↗pdf ↗

We study the problem of using causal models to improve the rate at which good interventions can be learned online in a stochastic environment. Our formalism combines multi-arm bandits and causal inference to model a novel type of bandit feedback that is not exploited by existing approaches. We propose a new algorithm t…

2016-06-10abs ↗pdf ↗

New algorithms optimize risk-aware selection in uncertain rewards.

problem Balancing expected reward and risk in uncertain, potentially heavy-tailed rewards.
method Distribution oblivious algorithms that consider CVaR, not bound on moments/tails.
result Provable upper bounds on incorrect identification probability.

Algorithm discovers edges between pairs of nodes with limited queries.

problem Discovering good matches between pairs of entities with limited queries.
method Pair-matching problem as a multi-armed bandit with constraints, focusing on Stochastic Block Model.
result Sublinear regret achievable in Stochastic Block Model with two communities, with phase transition related to community detection.

DART optimizes subset selection in non-linear bandit problems.

problem Optimizing subset selection in non-linear bandit problems with correlated rewards.
method DART algorithm for combinatorial bandits without individual arm feedback or linearity assumption.
result DART achieves a regret bound of ildeO(KKNT) ilde{\mathcal{O}}(K\sqrt{KNT}).

TRIPLE efficiently optimizes prompts with a budget constraint.

problem Efficiently selecting good prompts from a pool of candidates.
method TRIPLE connects prompt optimization to best arm identification in MAB, leveraging BAI-FB tools.
result TRIPLE outperforms baselines on multiple tasks with limited budget constraints.

This paper analyzes the multi-armed bandit model using path-integral methods.

problem Understanding the stochastic dynamics and optimal strategies in multi-armed bandit problems.
method Path-integral analysis of statistical physics.
result Emergence of multimodal regret distribution with large regrets from exploitation of sub-optimal arms.

New algorithms identify Pareto optimal sets in multi-objective bandit problems.

problem Identifying Pareto optimal sets in multi-objective bandit problems.
method Empirical Gap Elimination (EGE) algorithms combining hardness estimation and elimination schemes.
result Two EGE algorithms have exponentially decaying error probabilities with budget.

Dynamic ensemble active learning tackles non-stationary criteria in active learning.

problem Active learning's effectiveness varies across datasets and sessions, leading to suboptimal results.
method Developed a dynamic ensemble active learner based on a non-stationary multi-armed bandit with expert advice.
result Dynamic ensemble selects the best criteria at each step, improving overall performance.

Unified algorithm for efficient pure exploration using dual variables.

problem Efficiently achieving a specific goal through adaptive experimentation.
method Introducing dual variables to derive optimal allocation conditions, leading to Information-Directed Selection.
result Top-two Thompson sampling attains asymptotic optimality for Gaussian best-arm identification.

The paper addresses privacy-preserving BAI in clinical trials and user studies.

problem Privacy-preserving Best Arm Identification in adaptive clinical trials and user studies.
method The paper derives lower bounds on sample complexity for BAI algorithms with differential privacy constraints and proposes private variants of Top Two algorithms.
result Private variants of Top Two algorithms achieve asymptotic optimality in terms of sample complexity for BAI problems under differential privacy constraints.

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

problem Privacy-protected Best Arm Identification (BAI) in data-sensitive applications.
method Derives lower bounds on sample complexity, proposes AdaP-TT algorithm with Laplace noise, and validates with experiments.
result AdaP-TT matches the sample complexity lower bound up to constants in the high-privacy regime.

New algorithm tackles unknown utility network resource allocation.

problem Maximizing network utility with unknown agent utilities.
method Modeling as a bandit problem, proposing algorithms for resource allocation.
result Proposed algorithms are optimal when all agents have the same utility.