{"total":31,"rows":[{"id":"2206.13687","title":"POEM: Out-of-Distribution Detection with Posterior Sampling","created":"2022-06-28","cited_by_count":108,"area":null},{"id":"2205.01970","title":"Non-Stationary Bandit Learning via Predictive Sampling","created":"2022-05-04","cited_by_count":21,"area":null},{"id":"2101.09855","title":"Weak Signal Asymptotics for Sequentially Randomized Experiments","created":"2021-01-25","cited_by_count":14,"area":null},{"id":"2106.07914","title":"Control Variates for Slate Off-Policy Evaluation","created":"2021-06-15","cited_by_count":13,"area":null},{"id":"2107.00680","title":"A Map of Bandits for E-commerce","created":"2021-07-01","cited_by_count":9,"area":null},{"id":"2310.18465","title":"Nearly Minimax Optimal Submodular Maximization with Bandit Feedback","created":"2023-10-27","cited_by_count":7,"area":null},{"id":"2103.01453","title":"Efficient Optimal Selection for Composited Advertising Creatives with Tree Structure","created":"2021-03-02","cited_by_count":5,"area":null},{"id":"2406.10131","title":"Linear Contextual Bandits with Hybrid Payoff: Revisited","created":"2024-06-14","cited_by_count":5,"area":null},{"id":"2504.16397","title":"Compass: SLO-aware Query Planner for Compound AI Serving at Scale","created":"2025-04-23","cited_by_count":5,"area":null},{"id":"2211.02052","title":"Theta-Resonance: A Single-Step Reinforcement Learning Method for Design Space Exploration","created":"2022-11-03","cited_by_count":4,"area":null},{"id":"2407.20124","title":"AxiomVision: Accuracy-Guaranteed Adaptive Visual Model Selection for Perspective-Aware Video Analytics","created":"2024-07-29","cited_by_count":4,"area":null},{"id":"2202.06657","title":"The Impact of Batch Learning in Stochastic Linear Bandits","created":"2022-02-14","cited_by_count":3,"area":null},{"id":"2101.02553","title":"Off-Policy Evaluation of Slate Policies under Bayes Risk","created":"2021-01-05","cited_by_count":2,"area":null},{"id":"2307.15154","title":"A/B Testing and Best-arm Identification for Linear Bandits with Robustness to Non-stationarity","created":"2023-07-27","cited_by_count":2,"area":null},{"id":"2408.04251","title":"Cooperative Multi-Agent Deep Reinforcement Learning in Content Ranking Optimization","created":"2024-08-08","cited_by_count":2,"area":null},{"id":"2506.13163","title":"Efficient Algorithms for Logistic Contextual Slate Bandits with Bandit Feedback","created":"2025-06-16","cited_by_count":2,"area":null},{"id":"2108.05891","title":"Page-level Optimization of e-Commerce Item Recommendations","created":"2021-08-12","cited_by_count":1,"area":null},{"id":"2111.02071","title":"The Impact of Batch Learning in Stochastic Bandits","created":"2021-11-03","cited_by_count":1,"area":null},{"id":"2305.14704","title":"Practical Batch Bayesian Sampling Algorithms for Online Adaptive Traffic Experimentation","created":"2023-05-24","cited_by_count":1,"area":null},{"id":"2402.14301","title":"GenSERP: Large Language Models for Whole Page Presentation","created":"2024-02-22","cited_by_count":1,"area":null},{"id":"2107.00161","title":"The Use of Bandit Algorithms in Intelligent Interactive Recommender Systems","created":"2021-07-01","cited_by_count":0,"area":null},{"id":"2107.00204","title":"Markov Decision Process modeled with Bandits for Sequential Decision Making in Linear-flow","created":"2021-07-01","cited_by_count":0,"area":null},{"id":"2108.09076","title":"PASTO: Strategic Parameter Optimization in Recommendation Systems -- Probabilistic is Better than Deterministic","created":"2021-08-20","cited_by_count":0,"area":null},{"id":"2302.02579","title":"Recommender Systems: A Primer","created":"2023-02-06","cited_by_count":0,"area":null},{"id":"2307.14628","title":"Rapid and Scalable Bayesian AB Testing","created":"2023-07-27","cited_by_count":0,"area":null},{"id":"2309.08159","title":"AdSEE: Investigating the Impact of Image Style Editing on Advertisement Attractiveness","created":"2023-09-15","cited_by_count":0,"area":null},{"id":"2406.10795","title":"Improving Reward-Conditioned Policies for Multi-Armed Bandits using Normalized Weight Functions","created":"2024-06-16","cited_by_count":0,"area":null},{"id":"2409.15143","title":"Designing an Interpretable Interface for Contextual Bandits","created":"2024-09-23","cited_by_count":0,"area":null},{"id":"2510.07208","title":"A Broader View of Thompson Sampling","created":"2025-10-08","cited_by_count":0,"area":null},{"id":"2602.02514","title":"Design and Evaluation of Whole-Page Experience Optimization for E-commerce Search","created":"2026-01-23","cited_by_count":0,"area":null},{"id":"2606.31449","title":"Contextual Slate GLM Bandits with Limited Adaptivity","created":"2026-06-30","cited_by_count":0,"area":null}],"next_cursor":null}