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.

168,742 papers · 148 categories

Trend · papers per month

97195292389 · Jun 202019922001200920172026
48 results for robust multi-armed bandits

Improved εε-greedy handles strategic bidding in PPC auctions.

problem Strategic bidding in PPC auctions with personalization and corruptions.
method Extended εε-greedy to handle strategic arms in contextual multi-arm bandit.
result εε-greedy is robust to adversarial corruptions and degrades linearly with corruption.

New algorithms for best arm identification in bandits robust to misspecified parameters.

problem Inconsistent learning performance of traditional MAB algorithms when parameters are misspecified.
method Proposes two classes of asymptotically near-optimal algorithms for statistically robust MAB under fixed-budget pure exploration.
result Establishes fundamental performance limits and proposes algorithms that are asymptotically near-optimal.

New algorithm prevents strategic replication in multi-armed bandit problems.

problem Strategic replication by agents can exploit bandit algorithms' balance.
method Designs Hierarchical UCB (H-UCB) and Robust Hierarchical UCB (RH-UCB) algorithms.
result Achieves O(lnT)O(\ln T)-regret and sublinear regret in realistic scenarios.

The paper shows optimal robustness against adversarial corruption in sequential decision-making problems.

problem Optimal robustness to adversarial corruption in online decision-making problems.
method Investigates prediction with expert advice and multi-armed bandit problems, focusing on algorithms with decreasing learning rates and second-order regret bounds.
result Optimal robustness can be expressed by a square-root dependency on the amount of corruption, achieving O(logNΔ+ClogNΔ)O(\frac{\log N}{\Delta} + \sqrt{\frac{C \log N}{\Delta}})-regret.

This paper studies the deviations of the regret in a stochastic multi-armed bandit problem. When the total number of plays n is known beforehand by the agent, Audibert et al. (2009) exhibit a policy such that with probability at least 1-1/n, the regret of the policy is of order log(n). They have also shown that such a …

2011-07-22abs ↗pdf ↗

A robust bandit algorithm uses Dirichlet sampling to minimize regret under various distributional assumptions.

problem Robustness of bandit algorithms to model misspecification.
method Dirichlet Sampling (DS) algorithm based on pairwise comparisons and re-sampling of arm observations.
result Different DS variants achieve optimal regret guarantees for bounded distributions and logarithmic regret for semi-bounded distributions.

Paper develops robust estimators and strategies for stochastic MABs with heavy-tailed rewards.

problem Stochastic multi-armed bandits with heavy-tailed rewards.
method Proposes a novel robust estimator and perturbation-based exploration strategy.
result Develops upper and lower regret bounds for various perturbations.

Study on reward poisoning attacks on CMAB, revealing attackability depends on adversary's knowledge.

problem Reward poisoning attacks on Combinatorial Multi-Armed Bandits (CMAB).
method Provided a sufficient and necessary condition for attackability, devised an attack algorithm.
result Attackability of CMAB depends on adversary's knowledge of the bandit instance.

Paper tackles robust batched bandits for heavy-tailed rewards.

problem Clinical trials and other applications with heavy-tailed rewards.
method Proposes robust batched bandit algorithms for heavy-tailed rewards in finite-arm and Lipschitz-continuous settings.
result Heavier-tailed rewards require fewer batches for near-optimal regret in the instance-independent regime and Lipschitz setting.

Algorithm identifies best arm with prior info in structured bandits.

problem Bayesian fixed-budget best-arm identification in structured bandits.
method Prior-dependent allocations based on structure and prior information.
result Improved theoretical bounds and robust performance across diverse models.

New algorithm reduces regret in multi-agent bandits with malicious agents.

problem Collaboration between honest and malicious agents in multi-armed bandits.
method Dynamic reduction of communication with malicious agents, learning who is malicious.
result Algorithm reduces regret even with a single malicious agent, assuming mm is small compared to KK.

Bandit algorithms struggle with consistent performance and robustness.

problem Achieving consistent and robust performance in stochastic multi-armed bandit settings.
method Analyzing regret minimization trade-offs and proposing distribution-oblivious algorithms.
result Logarithmic regret is inconsistent and super-logarithmic regret is necessary for consistent learning.

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

problem Optimizing multi-armed bandit performance in both stochastic and adversarial environments.
method Follow-the-regularized-leader method with adaptive learning rates.
result First BOBW algorithm with gap-variance-dependent regret bounds in adversarial settings.

Paper uses subjective logic to estimate uncertainty in multi-armed bandit problems.

problem Estimating uncertainty in multi-armed bandit problems.
method Formalism of subjective logic applied to multi-armed bandits, proposing new algorithms.
result Subjective logic quantities enable useful assessment of uncertainty.

Quantum algorithms for multi-armed bandits are explored with limited reward access.

problem Exploring quantum speed-ups in multi-armed bandit problems with limited reward information.
method Introduced new bandit models and showed query complexity equivalence with classical algorithms.
result No quadratic speed-up is possible for multi-armed bandits with limited reward access.

Study on Pareto optimality in multi-objective bandit problems.

problem Pareto optimality in multi-objective multi-armed bandit problems.
method Formulated adversarial multi-objective multi-armed bandit, defined Pareto regrets, presented algorithms, established upper and lower bounds.
result New algorithms are optimal in adversarial settings and nearly optimal in stochastic settings.

RAVEN-UCB addresses non-stationary MAB problems with tighter regret bounds.

problem Non-stationary environments in multi-armed bandits.
method Combines variance-aware adaptation with three innovations: confidence bounds, adaptive control, and recursive updates.
result Achieves tighter regret bounds than UCB1 and UCB-V.

Paper proposes an efficient bandit-based algorithm for hyperparameter optimization.

problem Efficiently evaluating hyperparameters in deep learning models with large search spaces.
method Sub-Sampling (SS) algorithm combined with Bayesian Optimization (BOSS).
result Theoretical proof of optimality and empirical validation of superior performance.

Study finds optimal regret bound for multi-armed bandit problem with expert advice.

problem Optimizing decision-making in a multi-armed bandit problem with expert advice.
method Proved a tight lower bound matching the upper bound of Kale (2014) for minimax expected regret.
result The minimax optimal expected regret is Θ(√(T K log (N/K))) for the problem.

The paper tackles lifelong learning in multi-armed bandits, aiming to minimize average regret over multiple tasks.

problem Minimizing average regret in multi-armed bandits over multiple tasks.
method Confidence interval tuning of UCB algorithms and greedy algorithms applied to a bandit over bandit approach.
result Empirical improvement over previous work in the mortal bandit problem.

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.

Study collaborative learning among multi-agents in multi-armed bandits.

problem Minimizing group cumulative regret in a heterogeneous multi-agent setting.
method Developed decentralized algorithms for collaboration between NN agents learning MM stochastic multi-armed bandits.
result Proved near-optimal behavior of proposed algorithms for group regret.

New algorithm for nonstationary multi-armed bandits with optimal performance.

problem Nonstationary multi-armed bandits with changing model parameters over time.
method Adaptive Resetting Bandit (ADR-bandit) algorithm using adaptive windowing techniques.
result ADR-bandit achieves nearly optimal performance in both abrupt and gradual changes.

Drawing a sample from a discrete distribution is one of the building components for Monte Carlo methods. Like other sampling algorithms, discrete sampling suffers from the high computational burden in large-scale inference problems. We study the problem of sampling a discrete random variable with a high degree of depen…

2015-06-30abs ↗pdf ↗

Paper tackles transfer learning for contextual multi-armed bandits under covariate shift.

problem Nonparametric contextual multi-armed bandits with covariate shift.
method Established minimax rate of convergence, proposed transfer learning algorithm.
result Achieved near-optimal statistical guarantees for learning in target domain.

Proposes Genetic Thompson Sampling for multi-armed bandits, improving performance in nonstationary settings.

problem Improving sequential decision making tasks of online learning agents using multi-armed bandits.
method Integrates genetic principles into Thompson Sampling for multi-armed bandits.
result Significantly outperforms baselines in nonstationary settings.

In this paper, we study the multi-armed bandit problem in the batched setting where the employed policy must split data into a small number of batches. While the minimax regret for the two-armed stochastic bandits has been completely characterized in \cite{perchet2016batched}, the effect of the number of arms on the re…

2019-04-03abs ↗pdf ↗

This paper applies Thompson Sampling to asymmetric α\alpha-stable bandits for financial and wireless data.

problem Optimizing exploration-exploitation in multi-armed bandits with asymmetric α\alpha-stable distributions.
method Thompson Sampling applied to unknown asymmetric α\alpha-stable reward distributions.
result Demonstrates effectiveness of Thompson Sampling for asymmetric α\alpha-stable bandits.

The paper examines how loss aversion impacts multi-armed bandit decisions over long periods.

problem The impact of loss aversion on multi-armed bandit decisions over long periods.
method A new central limit theorem for measures with history-dependent variances, derived under risk aversion in gains and risk loving in losses.
result Consequences of loss aversion for asymptotic properties are derived in analytical results.

Two non-communicating players minimize regret in a multi-armed bandit game.

problem Optimal regret in non-communicating multi-armed bandit players.
method Proposed a strategy with no collisions, achieving near-optimal regret.
result Near-optimal regret of O(Tlog(T))O(\sqrt{T \log(T)}) with very high probability.