New bandit algorithms focus on extreme values, outperforming existing methods.
problem Optimizing decisions based on extreme values rather than expected values.
method Robust statistics-based algorithms with vanishing extremal regret.
result The proposed algorithms achieve superior performance compared to existing methods.
Study on private and robust multi-armed bandits with contaminated heavy-tailed rewards.
problem Private and robust multi-armed bandits with contaminated heavy-tailed rewards.
method Proposed a meta-algorithm with a private and robust mean estimation sub-routine exttt{PRM}.
result Achieved nearly-optimal regret for two heavy-tailed settings.
The paper provides robustness guarantees for mode estimation in bandits.
problem Understanding robustness in mode estimation under adversarial data contamination.
method Simple randomization and theoretical analysis of multi-armed bandits.
result Regret guarantees for various modal bandit problems.
Improved ε ε ε -greedy handles strategic bidding in PPC auctions.
problem Strategic bidding in PPC auctions with personalization and corruptions.
method Extended ε ε ε -greedy to handle strategic arms in contextual multi-arm bandit. result ε ε ε -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 bandit problem for finding best group of arms with worst mean reward.
problem Finding the best group of arms with the worst mean reward in overlapping groups.
method Two algorithms based on successive elimination and robust optimization.
result Upper bounds on the number of samples to find max-min optimal or near-optimal group.
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 ( ln T ) O(\ln T) O ( ln T ) -regret and sublinear regret in realistic scenarios. New model for display advertising with stochastic and adversarial components.
problem Display advertising with stochastic and adversarial click-through-rates.
method Adversarial scaling model; two algorithms tested: action elimination and mirror descent.
result Two algorithms are robust to adversarial scaling.
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 ( log N Δ + C log N Δ ) O(\frac{\log N}{\Delta} + \sqrt{\frac{C \log N}{\Delta}}) O ( Δ l o g N + Δ C l o g N ) -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 …
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.
New dynamic allocation methods for multi-armed bandit models.
problem Dynamic allocation problems in multi-armed bandit models.
method New types of dynamic allocation problems and proofs for Gittins index decomposition.
result New proofs for Gittins index decomposition and related results.
PAC-Bayesian analysis improves lifelong learning in multi-armed bandits.
problem Improving lifelong learning in multi-armed bandits.
method PAC-Bayesian analysis for deriving lower bounds and proposing lifelong learning algorithms.
result Proposed algorithms outperform baseline methods in lifelong multi-armed bandit problems.
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 m m m is small compared to K K K . 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.
Algorithm improves multi-armed bandit performance by transferring reward samples.
problem Sequential multi-armed bandit problem with changing reward distributions.
method UCB algorithm with reward sample transfer.
result Significant improvement in cumulative regret over standard UCB.
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.
Unified formulation bridges adversarial and nonstationary bandits.
problem Handling time-varying reward distributions in multi-armed bandit problems.
method Unified oracle that switches between adversarial and nonstationary bandit oracles based on window size.
result Optimal regret achieved with matching lower bound.
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.
In this paper we propose a multi-armed bandit inspired, pool based active learning algorithm for the problem of binary classification. By carefully constructing an analogy between active learning and multi-armed bandits, we utilize ideas such as lower confidence bounds, and self-concordant regularization from the multi…
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.
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 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 N N N agents learning M M M stochastic multi-armed bandits. result Proved near-optimal behavior of proposed algorithms for group regret.
New algorithm reduces worst-case regret for heavy-tailed bandits.
problem Stochastic Multi-Armed Bandit problem with heavy-tailed rewards.
method Modified minimax policy MOSS with saturated empirical mean.
result Worst-case regret matching lower bound for heavy-tailed distributions.
The paper explores sampling problems and shows minimal exploration is needed.
problem Exploration-exploitation trade-off in sampling.
method Systematic definition of regret, proposal of a simple algorithm.
result Near-optimal regret bounds achieved with minimal exploration.
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…
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.
New method for contextual bandits with corrupted context.
problem Contextual bandits with corrupted context in online settings.
method Combining contextual bandit and multi-armed bandit approaches.
result Improved learning from all iterations, including corrupted ones.
We present a formal model of human decision-making in explore-exploit tasks using the context of multi-armed bandit problems, where the decision-maker must choose among multiple options with uncertain rewards. We address the standard multi-armed bandit problem, the multi-armed bandit problem with transition costs, and …
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…
Sequential portfolio selection has attracted increasing interests in the machine learning and quantitative finance communities in recent years. As a mathematical framework for reinforcement learning policies, the stochastic multi-armed bandit problem addresses the primary difficulty in sequential decision making under …
New framework improves learning across multiple distributions.
problem Modeling uncertainty in sensitive machine learning applications.
method Inspired by multi-armed bandits, provides distribution-dependent guarantees.
result Enhanced dependence on suboptimality gaps and sample size.
In recent years, multi-armed bandit (MAB) framework has attracted a lot of attention in various applications, from recommender systems and information retrieval to healthcare and finance, due to its stellar performance combined with certain attractive properties, such as learning from less feedback. The multi-armed ban…
This paper applies Thompson Sampling to asymmetric α \alpha α -stable bandits for financial and wireless data.
problem Optimizing exploration-exploitation in multi-armed bandits with asymmetric α \alpha α -stable distributions. method Thompson Sampling applied to unknown asymmetric α \alpha α -stable reward distributions. result Demonstrates effectiveness of Thompson Sampling for asymmetric α \alpha α -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 ( T log ( T ) ) O(\sqrt{T \log(T)}) O ( T log ( T ) ) with very high probability.