arXiv AI
Jun 29
The Minimal Search Space for Conditional Causal Bandits
arXiv:2502. 06577v3 Announce Type: replace-cross Abstract: Causal knowledge can be used to support decision-making problems.
Information-Directed Sampling for Causal Bandits
arXiv:2607. 15577v1 Announce Type: cross Abstract: Causal bandits exploit structural relationships among variables to share information across interventions and accelerate the identification of high-reward decisions.
Related stories
arXiv Machine Learning
Jun 2
Evaluating and Learning Robust Bandit Policies Under Uncertain Causal Mechanisms
arXiv:2508. 02812v3 Announce Type: replace Abstract: Causal graphical models can encode large amounts structural knowledge, both from the background knowledge of domain experts and the structural knowledge discovered from randomized experiments or observational data.
arXiv Machine Learning
Jun 2
Bandit Simulation for Average Reward Inference
arXiv:2606. 00913v1 Announce Type: cross Abstract: Multi-arm bandit algorithms are increasingly used in online platforms, clinical trials, and social science experiments, but valid statistical inference on their performance remains an open challenge.
arXiv Machine Learning
Jul 31
On-Policy and Off-Policy Learning for Large Action Spaces
arXiv:2607. 28408v1 Announce Type: new Abstract: This thesis studies policy learning in interactive systems where an agent observes a context, selects an action from a very large set, and receives partial feedback.
arXiv AI
Jun 2
Transferring Information Across Interventions in Causal Bayesian Optimization
arXiv:2606. 01457v1 Announce Type: new Abstract: Bayesian optimization is a popular way to optimize expensive systems, where every experiment, simulation, or intervention costs time or money.
arXiv AI
3d ago
On the Complexity of Preference-Based Bandits
The paper investigates preference-based bandits where a learner selects pairs of arms and receives binary preference feedback modeled by Bradley–Terry. It introduces the locally sensitive eluder dimension, a new complexity measure for logistic preference feedback, and proposes the GINOP algorithm that uses log-loss confidence sets to balance optimism and exploration. The authors prove a first-order regret bound showing that learning with preference feedback can be as statistically efficient as learning from direct rewards, and they validate their theory with empirical experiments.
arXiv Machine Learning
Sep 25
Exact Bayes Regret and Asymptotic Optimality in High-Dimensional Gaussian Bandits
The paper analyzes Bayesian linear bandits with isotropic Gaussian parameters, independent Gaussian arms, and Gaussian reward noise when the time horizon scales with the dimension. It derives explicit limits for the normalized posterior uncertainty and parameter overlaps, yielding exact regret curves for several policies—including Thompson sampling, posterior‑mean greedy selection, and scaled‑covariance variants. The results show that posterior‑mean greedy selection achieves the optimal Bayes regret, while Thompson sampling incurs a strictly larger leading regret whose ratio to greedy lies between one and two, approaching two for long horizons.
arXiv Machine Learning
Aug 12
Weighted Sequential Bayesian Inference for Non-Stationary Linear Contextual Bandits
arXiv:2307. 03587v4 Announce Type: replace Abstract: In non-stationary linear contextual bandits, existing efficient algorithms typically rely on the Weighted Regularized Least-Squares (WRLS) estimator.
arXiv Machine Learning
Sep 22
Causal Bayesian Optimization: Foundations, Methods, and Applications
arXiv:2609.24112v1 Announce Type: cross Abstract: Causal Bayesian Optimization (CBO) combines causal inference with Bayesian optimization to enable sample-efficient intervention selection in systems...
arXiv AI
Jul 7
Fixed-Confidence Best-Arm Identification for Causal Mediation Analysis
arXiv:2607. 04315v1 Announce Type: cross Abstract: This paper studies the problem of identifying the treatment that maximizes the expected natural direct potential outcome (NDPO), which captures the potential outcome of an intervention while excluding the pathway transmitted through a mediator that researchers may wish to remove from evaluation.
arXiv Machine Learning
Aug 19
Latent Order Bandits
The paper introduces Latent Order Bandits (LOB), a new bandit framework that relaxes the strict assumptions of traditional latent bandits by only requiring a partial order of action preferences within each latent state. LOB allows instances sharing the same state to have different reward distributions as long as the action ranking remains consistent, making it suitable for scenarios like user groups on streaming services who agree on genre preferences but rate differently. The authors present an upper‑confidence bound algorithm for both total and partial latent orders, provide regret bounds, and propose a posterior‑sampling variant that empirically outperforms full‑prior latent bandits when reward scales vary across instances sharing the same latent state.
arXiv Machine Learning
Sep 16
Meta-LinEXP3: Online-within-Online Learning for Adversarial Linear Contextual Bandits
Meta-LinEXP3 is an online-within-online algorithm designed for adversarial linear contextual bandits with random action sets. It builds a task-level prior from completed tasks to guide an inner LinEXP3 learner, achieving an σO(√n) per‑task regret when context distributions are known and an σO(n^{2/3}) regret with a past‑only regularized moment estimator when they are unknown. The paper also links prior accuracy to transfer regret, showing that better priors yield sublinear, transfer‑dependent regret across tasks, and demonstrates the method on structured hyperspectral tensor sampling.