A new algorithm picks two items for users based on context, achieving better performance than existing methods.
problem Picking two items from a set for users with contextual input and user choice.
method A second-order algorithm framework using relative upper-confidence bounds for exploration and exploitation.
result Regret bound of O ( Q T + T Q T log T + T log T ) O(Q_T + \sqrt{TQ_T\log T} + \sqrt{T}\log T) O ( Q T + T Q T log T + T log T ) , demonstrating improved performance. The paper honors Lai's contributions to multi-armed bandits and establishes new regret bounds.
problem Improving regret bounds in multi-armed bandit problems.
method Establishes non-asymptotic regret bounds for upper confidence bound indices.
result New regret bounds match Lai-Robbins lower bound.
Proof connects Gittins indices to Bayesian upper confidence bounds for patient agents.
problem Connecting Gittins indices to Bayesian upper confidence bounds for patient agents.
method Proof using Gaussian multi-armed bandit problem with discount factor γ.
result Gittins index equals γ-quantile of posterior mean plus vanishing error term.
New acquisition function for extreme rewards in bandits.
problem Online decision making with extreme payoffs in multi-armed bandits.
method Modeling payoffs as Gaussian processes and using a novel UCB acquisition function.
result Demonstrated benefits across synthetic and real-world benchmarks.
Paper improves regret bounds for Gaussian process upper confidence bound in Bayesian optimization.
problem Minimizing regret in Gaussian process bandit optimization.
method Gaussian process upper confidence bound (GP-UCB) algorithm with refined analysis.
result Achieves O ( T ln 2 T ) O(\sqrt{T \ln^2 T}) O ( T ln 2 T ) cumulative regret under squared exponential kernel. Improved Bayesian optimisation method using randomised Gaussian process UCB.
problem Improving performance in Bayesian optimisation.
method Developed a modified Gaussian process upper confidence bound (GP-UCB) acquisition function.
result The method achieves better performance than GP-UCB in various problems.
Two batch Bayesian optimization algorithms with regret guarantees.
problem Efficiently optimizing multiple objectives in batch feedback settings.
method Gaussian process upper confidence bound and Thompson sampling approaches.
result Frequentist regret guarantees and numerical results.
Bayesian methods improve drug discovery experiment design.
problem Optimizing drug screening experiments in high-dimensional data.
method Bayesian inference and optimisation with upper confidence bound algorithms, Thompson sampling, and sparse tree search.
result Sparse tree search techniques outperform other methods in drug toxicity screening.
New algorithm optimizes bandit problems with upper-confidence bounds.
problem Optimizing global loss functions with bandit feedback.
method Upper-Confidence Frank-Wolfe algorithm for general functions.
result Theoretical guarantees for algorithm performance.
The estimation of probabilities of default (PDs) for low default portfolios by means of upper confidence bounds is a well established procedure in many financial institutions. However, there are often discussions within the institutions or between institutions and supervisors about which confidence level to use for the…
One-bit feedback suffices for a bandit problem's optimal strategy.
problem Optimal strategy for multi-armed bandit problem with limited feedback.
method Coding and decoding schemes for one-bit feedback to mimic full-reward feedback.
result Regret ratio approaches 1 with one-bit feedback.
A new method optimizes robustness measures under input uncertainty using randomized Gaussian process upper confidence bound.
problem Optimizing robustness measures under input uncertainty.
method Randomized robustness measure GP-UCB (RRGP-UCB) that samples β from a chi-squared-based distribution.
result RRGP-UCB provides tight bounds on expected regret.
TS-UCB improves Thompson Sampling with minimal extra computation.
problem Online decision problems with bandit feedback.
method TS-UCB uses posterior samples and upper confidence bounds to select arms.
result TS-UCB achieves lower regret on various datasets.
Efficiently reduces training and inference costs by dynamically selecting important channels.
problem Reducing memory and computational demands for neural network training and inference.
method Integrates pruning into training by selecting only highly salient channels for execution, using combinatorial upper confidence bound algorithm.
result Reduces computational cost up to 4x and parameter count up to 9x.
UCB-RS uses RS to improve UCB for online advertising.
problem Improving recommendation in online advertising.
method UCB-RS, combining UCB with recommendation system.
result UCB-RS outperforms other reinforcement learning methods in RecoGym.
New algorithm reduces regret in generalized linear contextual bandits.
problem Optimizing rewards in binary reward contexts with feature vectors.
method Upper confidence bound algorithm for generalized linear models.
result Achieves optimal regret of i l d e O ( d T ) ilde{O}(\sqrt{dT}) i l d e O ( d T ) . This paper is devoted to regret lower bounds in the classical model of stochastic multi-armed bandit. A well-known result of Lai and Robbins, which has then been extended by Burnetas and Katehakis, has established the presence of a logarithmic bound for all consistent policies. We relax the notion of consistence, and e…
AdaLinUCB optimizes exploration-exploitation for contextually varying costs.
problem Optimizing decision-making in environments with varying exploration costs.
method Adaptive Upper-Confidence-Bound (AdaLinUCB) algorithm for opportunistic learning.
result AdaLinUCB achieves O((log T)^2) regret bound, significantly outperforming other algorithms.
EBUCB framework achieves optimal regret with bounded approximate inference error.
problem Theoretical gap between practical performance and theoretical justification of Bayesian bandit algorithms with approximate inference.
method Enhanced Bayesian Upper Confidence Bound (EBUCB) framework that accommodates bandit problems with approximate inference.
result EBUCB achieves optimal regret order O ( log T ) O(\log T) O ( log T ) under certain conditions on inference error. Bayesian bandit algorithms with approximate inference improve regret bounds in stochastic linear bandits.
problem Theoretical justification for Bayesian bandit algorithms with approximate inference in stochastic linear bandits.
method Proposed a theoretical framework to analyze approximate inference impact and conducted frequentist regret analysis on LinTS and LinBUCB.
result LinTS and LinBUCB preserve their original regret upper bounds with larger constant terms in approximate inference settings.
A new algorithm for better decision-making in recommendation systems.
problem Stochastic multi-armed bandit problem and cold start problem in recommender systems.
method Proposes Hellinger-UCB, a variant of UCB algorithm using squared Hellinger distance.
result Hellinger-UCB reaches the theoretical lower bound and outperforms other algorithms in practical applications.
UCB algorithm provides stable sample means for sequential data.
problem Challenges in inferential tasks with sequential data.
method Stability property of UCB algorithm for multiarmed bandit problems.
result UCB algorithm ensures asymptotically normal sample means.
Bayes-UCBVI tackles reinforcement learning with a new upper confidence bound method.
problem Optimizing exploration in reinforcement learning without bonuses.
method Bayes-UCBVI uses a quantile of a Q-value function posterior as an upper confidence bound.
result Proves a regret bound of order O ~ ( H 3 S A T ) \widetilde{O}(\sqrt{H^3SAT}) O ( H 3 S A T ) for tabular reinforcement learning. New algorithm reduces regret and constraint violation in adversarial CMDP learning.
problem Online learning for episodic stochastically constrained Markov decision processes (CMDPs) with adversarial loss.
method Upper Confidence Primal-Dual Reinforcement Learning (UC-PDL) algorithm.
result Achieves O ~ ( L ∣ S ∣ ∣ A ∣ T ) \widetilde{\mathcal{O}}(L|\mathcal{S}|\sqrt{|\mathcal{A}|T}) O ( L ∣ S ∣ ∣ A ∣ T ) upper bounds of both regret and constraint violation. This paper improves GP-UCB by using a shifted exponential distribution for confidence parameters.
problem Theoretical confidence parameter in GP-UCB increases with iterations, leading to large values.
method Introduced IRGP-UCB, a randomized variant of GP-UCB using a shifted exponential distribution for confidence parameters.
result IRGP-UCB achieves sub-linear regret without increasing the confidence parameter.
Paper proposes a new UCB approach for estimating maximum mean.
problem Estimating the maximum mean in various applications.
method Upper Confidence Bound (UCB) approach with adaptive sampling.
result LSA estimator shows faster bias decay compared to GA.
CRB tackles rising rewards in combinatorial online learning.
problem Rising rewards in combinatorial online learning.
method CRB framework and CRUCB algorithm.
result Empirical and theoretical validation of CRUCB's effectiveness.
Proposes a new UCB algorithm using bootstrap for online decision making.
problem Improving exploration in online decision making with partial feedback.
method Non-parametric, data-dependent UCB algorithm based on multiplier bootstrap with second-order correction.
result Significant regret reductions in multi-armed and linear bandit problems.
Efficiently identifies good policies by choosing contexts for human feedback.
problem Efficiently identifying good policies in applications with high feedback costs.
method Introduces offline contextual dueling bandit setting and an upper-confidence-bound style algorithm.
result Proves a regret bound and shows superior performance over uniformly sampled contexts.
New bounds for Bayesian bandits show prior improves performance.
problem Improving regret bounds for Bayesian bandits.
method Upper confidence bound algorithm with finite-time logarithmic regret bounds.
result Derives O ( c Δ log n ) O(c_Δ\log n) O ( c Δ log n ) and O ( c h log 2 n ) O(c_h \log^2 n) O ( c h log 2 n ) upper bounds for Bayesian bandits. Two new algorithms reduce group regret in abruptly changing multi-player bandit problems.
problem Reducing group regret in multi-player bandit problems in environments that change suddenly.
method Design of two novel algorithms: RR-SW-UCB# and SW-DLP.
result Expected cumulative group regret converges to zero over time.
Algorithm maximizes rewards with a budget and giving up option.
problem Sequential decision-making with stochastic rewards and resource consumption.
method Upper Confidence Bound (UCB) algorithm for maximizing cumulative reward.
result Logarithmic regret bound with improved dependence on problem parameters.
Improved BO algorithms reduce prediction error under Gaussian noise.
problem Reducing prediction error in Bayesian optimization with Gaussian noise.
method Established new prediction error bounds for Gaussian process under frequentist setting.
result Proved improved convergence rates of cumulative regret for GP-UCB and GP-TS.
This paper proposes a DGP approach with UCBs for point target tracking over WSNs.
problem Uncertainty quantification in distributed machine learning-based tracking over WSNs.
method Distributed Gaussian process (DGP) approach with upper confidence bounds (UCBs).
result UCBs provide 88% and 42% higher probability of encompassing true target states in X and Y coordinates, respectively.
A bandit problem with filtered Poisson process data.
problem Maximizing points revealed from a continuum action space.
method Upper confidence bound algorithm with data-adaptive discretisation.
result Regret bound of O(T^(2/3)) under Lipschitz assumption.
Study optimal adaptive allocation for multi-armed bandits with Markovian rewards.
problem Optimal adaptive allocation for multi-armed bandits with Markovian rewards.
method Round-robin Kullback-Leibler upper confidence bounds for optimal adaptive allocation.
result Logarithmic dependence of regret on time horizon, asymptotically optimal.
Improved algorithm for Lipschitz bandit optimization with reduced complexity.
problem Efficiently solving the Lipschitz bandit optimization problem.
method Tree UCB-Hoeffding algorithm with adaptive partitions and tree-based search strategy.
result Achieves the regret lower bound up to a logarithmic factor with O ( T log T ) \mathcal{O}(T\log T) O ( T log T ) computational cost. FP-UCB algorithm achieves bounded regret for finitely parameterized multi-armed bandits.
problem Finitely parameterized multi-armed bandits with unknown but known parameter set.
method FP-UCB algorithm using structural information about the parameter set.
result FP-UCB achieves bounded regret under structural condition, logarithmic otherwise.
New method optimizes searchers' allocation on perimeters over time.
problem Optimizing searchers' allocation on perimeters to detect intrusions.
method Combinatorial multi-armed bandit (CMAB) with upper confidence bound approach.
result Upper and lower bounds on expected performance of the method.
This paper analyzes regret bounds for Gaussian process Thompson sampling.
problem Analyzing the performance of Gaussian process Thompson sampling (GP-TS) in Bayesian optimization.
method The paper derives several regret bounds for GP-TS, including a lower bound, upper bounds on the second moment of cumulative regret, expected lenient regret, and improved cumulative regret.
result The paper provides improved regret upper bounds for GP-TS, showing that it suffers from a polynomial dependence on 1 / δ 1/δ 1/ δ with probability δ δ δ . Study of multi-armed bandits with state-switching rewards using Markov models.
problem Multi-armed bandit problem with state-switching rewards.
method Spectral method-of-moments estimations for hidden Markov models, belief error control, upper-confidence-bound methods.
result Upper bound of O ( T 2 / 3 log T ) O(T^{2/3}\sqrt{\log T}) O ( T 2/3 log T ) for the learning algorithm performance. This paper improves Bayesian optimization by using pseudo-points to enhance model accuracy.
problem Expensive black-box optimization problems, especially in parameter tuning and experimental design.
method Generates pseudo-points to improve Gaussian process models in Bayesian optimization.
result Cumulative regret can be generally upper bounded using the proposed framework.
Algorithm aggregates rewards from multiple players to learn related tasks in online bandit learning.
problem Learning related but slightly different tasks in an online setting with heterogeneous feedback.
method RobustAgg ( ε ) (ε) ( ε ) algorithm that aggregates rewards from different players. result Achieves instance-dependent regret guarantees and nearly matching lower bounds.
A framework for improving reward prediction in contextual bandits.
problem Improving reward prediction in contextual bandits with side information.
method Upper confidence bound-based multi-task learning algorithm for contextual bandits.
result Established a regret bound quantifying task similarity advantages.
A new UCB algorithm for heavy-tailed bandits with near-optimal regret.
problem Sequential decision making in uncertain environments with heavy-tailed rewards.
method Data-driven, distribution-free UCB algorithm combining resampled median-of-means and UCB.
result Near-optimal regret bound for heavy-tailed distributions.
A new federated multi-armed bandit framework with personalization balances generalization and personalization.
problem Balancing generalization and personalization in federated multi-armed bandits.
method Proposed a Personalized Federated Upper Confidence Bound (PF-UCB) algorithm to achieve a O ( log ( T ) ) O(\log(T)) O ( log ( T )) regret. result PF-UCB achieves an O ( log ( T ) ) O(\log(T)) O ( log ( T )) regret regardless of personalization degree and has similar instance dependency to lower bound. InfoTree improves reinforcement learning by optimizing tool use with a greedy submodular approach.
problem Maximizing information from tool use in reinforcement learning with limited resources.
method Formalizes Rollout Informativeness, recasts state selection as submodular maximization, and uses UUCB and ABA.
result InfoTree outperforms existing methods across various benchmarks, improving performance by 18.2% on average.
Study optimizes dynamic product selection and pricing using censored preference feedback.
problem Maximizing revenue from dynamic assortment and pricing decisions.
method Proposes a censored multinomial logit model and LCB pricing strategy combined with UCB or TS product selection.
result Achieves optimal regret bounds for dynamic pricing and selection.