New model tackles causal bandits with dependent variables.
problem Understanding reward-maximizing interventions in causal networks with dependent variables.
method Introduces hierarchical causal bandit model with a contextual variable capturing interactions among variables.
result Derives nearly matching regret bounds for binary context in causal bandits with dependent arms.
A new framework for structured bandits using influence diagrams and variational Thompson sampling.
problem Complex statistical dependencies in structured bandit problems.
method Influence diagram framework, variational Thompson sampling, tracking structured posterior distribution.
result Empirically evaluated algorithms perform as well as or better than existing baselines.
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.
The study explores whether model selection guarantees apply to contextual bandits.
problem Applying model selection guarantees to contextual bandits.
method Investigates whether similar guarantees for model selection in statistical learning can be extended to contextual bandit learning.
result Initial findings suggest that model selection guarantees may not directly apply to contextual bandits.
Contextual bandits require careful exploration vs. exploitation to avoid biased outcome model estimation.
problem Contextual bandits face challenges in estimating outcome models due to rich heterogeneity and complex models.
method Developed parametric and non-parametric contextual bandits integrating balancing methods from causal inference and econometrics.
result First regret bound analyses for contextual bandits with balancing show competitive performance.
Graph-Triggered Bandits unify rested and restless bandits with graph-defined arm interactions.
problem Modeling sequential decision-making problems with evolving arm rewards.
method Graph-Triggered Bandits (GTBs) framework that generalizes rested and restless bandits using a graph.
result Rested and restless bandits are special cases of GTBs for suitable graphs.
Factored bandits model learns with limited feedback using decomposable actions.
problem Limited feedback learning with decomposable actions.
method Introduces factored bandits model, provides anytime algorithm, and matching upper and lower bounds.
result Improves regret bounds for utility-based dueling bandits.
Efficiently handles contextual bandits with diffusion models.
problem Challenges in online decision-making with contextual bandits.
method Leverage pre-trained diffusion models as priors to capture action dependencies.
result Developed an algorithm for efficient posterior approximation.
The paper connects discrete choice models to multi-armed bandit algorithms with sublinear regret bounds.
problem Optimizing user choices in a multi-armed bandit setting.
method Establishes connections between discrete choice models and multi-armed bandit algorithms, providing sublinear regret bounds and novel algorithms.
result Sublinear regret bounds for a family of algorithms, including the Exp3 algorithm.
Study on indexability of restless multi-armed bandits and rollout policy performance.
problem Maximizing discounted rewards in finite state restless multi-armed bandit problems.
method Decouple the problem into single-armed restless bandits, analyze using value iteration, and compare with Whittle index policy.
result Demonstrates conditions for indexability and compares performance of index policy and rollout policy.
A new algorithm for conversational recommendation systems using dueling bandits in GLMs.
problem Limited user feedback in existing conversational bandit methods.
method Integrates dueling bandits with relative feedback in generalized linear models.
result Theoretical and empirical validation of ConDuel's efficacy.
Develops balanced linear contextual bandit algorithms to reduce estimation bias.
problem Estimation bias in contextual bandits with rich heterogeneity or complex models.
method Integrates balancing methods from causal inference to reduce estimation bias.
result First regret bound analyses for linear contextual bandits with balancing.
In this paper we propose a flexible and efficient framework for handling multi-armed bandits, combining sequential Monte Carlo algorithms with hierarchical Bayesian modeling techniques. The framework naturally encompasses restless bandits, contextual bandits, and other bandit variants under a single inferential model. …
New algorithm estimates treatment effects for more efficient contextual bandits.
problem Contextual bandits struggle with action-independent reward redundancies.
method Reduces contextual bandits to heterogeneous treatment effect estimation.
result Heterogeneous treatment effect estimation leads to more efficient model estimation.
New insights into multi-armed bandits with budget constraints.
problem Multi-armed bandits with supply/budget constraints.
method Characterization of logarithmic regret rates, simple regret, and reduction to other bandit problems.
result Full characterization of logarithmic, instance-dependent regret rates for BwK.
Master-slave architecture tackles combinatorial multi-armed bandits with diversity constraints.
problem Solving top- K K K combinatorial multi-armed bandits with non-linear feedback and diversity constraints. method Master-slave architecture with six slave models, teacher learning, and policy co-training.
result Significantly outperforms existing algorithms in synthetic and real datasets.
A meta-UCB method combines stochastic bandit algorithms.
problem Combining multiple stochastic bandit algorithms efficiently.
method Meta-UCB procedure solving an N-armed bandit problem.
result Final regret depends only on the best base algorithm's regret.
Bayesian bandits misspecification affects UX optimization, revealing new models.
problem Misspecification of value models in Bayesian bandits impacts UX optimization.
method Formulated UXO as a restless, sleeping bandit with unobserved confounders and optional stopping. Provided model extensions to address misspecifications.
result Common misspecifications lead to sub-optimal rewards, demonstrating overdispersion's effects on bandit performance.
The paper improves theoretical guarantees for Thompson Sampling in cascading bandits.
problem Optimizing online recommender systems with cascading bandits.
method Develops and analyzes new Thompson Sampling algorithms for cascading bandits.
result Establishes the first theoretical guarantees on Thompson Sampling for cascading bandits.
Bayesian optimization improved for biased data.
problem Adversarial bias in observations, especially hidden confounders.
method Reduction to dueling bandits, information-directed sampling (IDS).
result First efficient kernelized algorithm with regret guarantees.
New bandit algorithms improve sparse reward learning.
problem Sparse rewards hinder learning efficiency in real-world bandit applications.
method Developed algorithms based on Upper Confidence Bound and Thompson Sampling for zero-inflated distributions.
result Empirical performance of new algorithms is superior to existing methods.
New algorithms for model selection in linear contextual bandits without feature diversity conditions.
problem Model selection in linear contextual bandits without feature diversity conditions.
method Data-adaptive algorithms that provide model selection guarantees without feature diversity conditions.
result O(d^α T^{1-α}) model selection guarantees with no feature diversity conditions.
Study on selecting between base algorithms in stochastic bandit problems.
problem Model selection in stochastic environments with contextual information.
method Developed a meta-algorithm-base algorithm abstraction with a smoothing transformation for optimal O ( T ) O(\sqrt{T}) O ( T ) guarantees. result Optimal O ( T ) O(\sqrt{T}) O ( T ) model selection guarantees for stochastic contextual bandit problems. Chronological Causal Bandits (CCB) tackles dynamic causal decision-making.
problem Dynamic causal decision-making in a system where rewards depend on past interventions.
method Introduces a new MAB problem (Chronological Causal Bandit) where rewards are influenced by a dynamic causal model.
result Early findings show the CCB can transfer information between sequential MABs.
A framework for auto-tuning hyper-parameters in contextual bandit algorithms.
problem Auto-tuning hyper-parameters in real-time for contextual bandit algorithms.
method Proposes a Syndicated Bandits framework to learn multiple hyper-parameters dynamically.
result Achieves optimal regret bounds under certain scenarios and handles multiple contextual bandit algorithms.
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.
A new method for dueling bandits improves performance.
problem Improving decision-making in dueling bandits.
method Sup-KLUCB method for K-armed dueling bandits, converting Copeland dueling bandits into standard MAB problems.
result Sup-KLUCB outperforms state-of-the-art methods in Copeland dueling bandits.
This review examines bandit problems in AI using statistical methods.
problem Sequential decision-making under uncertainty in AI environments.
method Foundational models, concentration inequalities, minimax regret bounds, frequentist and Bayesian algorithms, K-armed contextual bandits, SCAB, functional data analysis.
result Exploration-exploitation trade-offs and regret analyses in various bandit problems.
A new algorithm solves a regional multi-armed bandit problem with group information.
problem Optimizing decisions with unknown parameters across groups.
method UCB-g algorithm combining UCB and greedy principles.
result Proves the order-optimality of UCB-g and establishes a matching lower bound.
Balances and eliminates base algorithms in bandits and RL to bound total regret.
problem Model selection in bandits and reinforcement learning with unknown optimal regret.
method Balances and eliminates base algorithms based on candidate regret bounds.
result Total regret bound is the best valid candidate regret bound times a small multiplicative factor.
Paper tackles domain adaptation for contextual bandits with sub-linear regret.
problem Adapting contextual bandit algorithms across domains with distribution shift.
method Learn a bandit model for the target domain using feedback from the source domain.
result Sub-linear regret bound maintained across domains.
A new recommendation system model tackles unreliable user behavior.
problem Creating effective recommendation systems in the presence of unreliable user behavior.
method A novel modification of Multi-Armed Bandits with an unreliable intermediate.
result Proved fundamental theorems and developed an Explore-Commit algorithm close to optimal performance.
Develops first optimal algorithm for logistic bandits.
problem Pure exploration in logistic bandits.
method Logistic track-and-stop (Log-TS) algorithm.
result Asymptotically matches lower bound for expected sample complexity.
Survey and compare PAC-Bayes bounds for bandit problems.
problem Designing and evaluating bandit algorithms with strong performance guarantees.
method PAC-Bayes bounds applied to bandit problems.
result PAC-Bayes bounds useful for offline bandit algorithms, but loose for online algorithms.
A new MDP with Bandits approach for sequential decision making in linear-flow scenarios.
problem Sequential decision making with limited feedback in a linear-flow context.
method Formulated as an MDP with Bandits, using Thompson sampling for action selection and exact dynamic programming for allocation.
result The proposed MDP with Bandits algorithm outperforms other methods in sequential decision making.
Two randomized algorithms improve regret bounds for generalized linear bandits.
problem Improving regret bounds for generalized linear bandits.
method Two randomized algorithms: GLM-TSL and GLM-FPL.
result Upper bounds of O ( d n log K ) O(d \sqrt{n \log K}) O ( d n log K ) on regret for both algorithms. A new algorithm selects models for contextual bandits, reducing regret.
problem Model selection for stochastic contextual bandits under realizability assumption.
method Adaptive Contextual Bandit (ACB) algorithm, successive refinement phases.
result ACB algorithm achieves similar regret bound to known algorithms, with a model selection cost.
This paper identifies the minimal set of nodes for optimal conditional interventions in causal bandits.
problem Optimizing decision-making in causal bandits with conditional interventions.
method Graphical characterization and efficient algorithm to identify the minimal set of nodes.
result The proposed algorithm significantly prunes the search space and accelerates convergence rates.
This paper tackles efficient federated learning for generalized linear bandits.
problem Limited communication efficiency restricts existing federated learning solutions to linear models.
method Proposes a communication-efficient solution framework using online and offline regression.
result Proves sub-linear regret and communication cost for generalized linear bandits.
BLOB combines organic and bandit signals for better user interest estimation.
problem Combining organic and bandit signals for improved user interest estimation.
method Bayesian Latent Organic Bandit (BLOB) model using variational auto-encoders and local re-parametrization.
result BLOB outperforms organic and bandit-based methods in both organic and bandit-rich environments.
OSOM solves multi-armed and linear contextual bandits efficiently.
problem Simultaneously optimal algorithm for multi-armed and linear contextual bandits.
method Design of a single computationally efficient algorithm that adapts to both regimes.
result Simultaneously optimal regret rates in both simple multi-armed and linear contextual bandits.
Proposes a new algorithm for non-stationary bandits.
problem Non-stationary reward distributions in contextual bandits.
method Multiscale changepoint detection for adaptive learning.
result Regret bound analysis and superior performance in experiments.
Paper presents adaptive Lipschitz bandit framework for efficient optimization.
problem Optimizing rewards and minimizing regret in stochastic Lipschitz bandit problems.
method Adaptive learning of partitions in context- and arm-space using hierarchical Bayesian models.
result Achieves state-of-the-art performance in real-world tasks like neural network hyperparameter tuning.
Greedy policies perform poorly in imperfectly observed contextual bandits.
problem Performance of Greedy policies in bandits with partially observed contexts.
method Analysis of Greedy reinforcement learning policies under imperfectly observed contextual bandits.
result Worst-case regret grows poly-logarithmically with the time horizon and the failure probability.
Regularized contextual bandits use bins to solve multi-armed bandit problems.
problem Contextual bandit problems with a known baseline policy.
method Nonparametric model, splitting context space into bins, solving bandit instances independently.
result Intermediate convergence rates interpolating between slow and fast rates.
Motivated by models of human decision making proposed to explain commonly observed deviations from conventional expected value preferences, we formulate two stochastic multi-armed bandit problems with distorted probabilities on the reward distributions: the classic K K K -armed bandit and the linearly parameterized bandit…
Deep learning tackles contextual multi-armed bandits with principled exploration.
problem Contextual multi-armed bandits in industrial applications.
method Bayesian neural network with dropout for non-linear modeling and Thompson sampling for principled exploration.
result Substantially reduces regret compared to existing methods.
New framework tackles submodular welfare with multi-agent combinatorial bandits.
problem Maximizing total welfare among agents with shared constraints and submodular utilities under bandit feedback.
method Proposes an explore-then-commit strategy with randomized assignments for multi-agent combinatorial bandits.
result Achieves i l d e O ( T 2 / 3 ) ilde{\mathcal{O}}(T^{2/3}) i l d e O ( T 2/3 ) regret, first for partition-based submodular welfare problem under bandit feedback.