{"list":"other","total":57,"rows":[{"id":"1912.13213","title":"Online Learning: A Modern Introduction Using Convex Optimization","created":"2019-12-31","cited_by_count":417},{"id":"2012.08507","title":"Nearly Minimax Optimal Reinforcement Learning for Linear Mixture Markov Decision Processes","created":"2020-12-15","cited_by_count":200},{"id":"2403.00409","title":"Provably Robust DPO: Aligning Language Models with Noisy Feedback","created":"2024-03-01","cited_by_count":135},{"id":"1803.09353","title":"Stochastic bandits robust to adversarial corruptions","created":"2018-03-25","cited_by_count":119},{"id":"2002.07530","title":"Improved Optimistic Algorithms for Logistic Bandits","created":"2020-02-18","cited_by_count":118},{"id":"1406.1853","title":"Model-based Reinforcement Learning and the Eluder Dimension","created":"2014-06-07","cited_by_count":116},{"id":"2001.09576","title":"Naive Exploration is Optimal for Online LQR","created":"2020-01-27","cited_by_count":116},{"id":"1507.08025","title":"Multi-armed Bandit Models for the Optimal Design of Clinical Trials: Benefits and Challenges","created":"2015-07-29","cited_by_count":114},{"id":"1902.08647","title":"Better Algorithms for Stochastic Bandits with Adversarial Corruptions","created":"2019-02-22","cited_by_count":92},{"id":"2107.05745","title":"Adapting to Misspecification in Contextual Bandits","created":"2021-07-12","cited_by_count":81},{"id":"2112.14368","title":"Adaptivity and Non-stationarity: Problem-dependent Dynamic Regret for Online Convex Optimization","created":"2021-12-29","cited_by_count":66},{"id":"2007.03285","title":"Stochastic Linear Bandits Robust to Adversarial Attacks","created":"2020-07-07","cited_by_count":65},{"id":"2010.12642","title":"Instance-Wise Minimax-Optimal Algorithms for Logistic Bandits","created":"2020-10-23","cited_by_count":57},{"id":"2205.11507","title":"Computationally Efficient Horizon-Free Reinforcement Learning for Linear Mixture MDPs","created":"2022-05-23","cited_by_count":52},{"id":"2205.06811","title":"Nearly Optimal Algorithms for Linear Contextual Bandits with Adversarial Corruptions","created":"2022-05-13","cited_by_count":51},{"id":"1605.08722","title":"An algorithm with nearly optimal pseudo-regret for both stochastic and adversarial bandits","created":"2016-05-27","cited_by_count":47},{"id":"2101.12745","title":"Improved Variance-Aware Confidence Sets for Linear Bandits and Linear Mixture MDP","created":"2021-01-29","cited_by_count":45},{"id":"2110.03580","title":"A Model Selection Approach for Corruption Robust Reinforcement Learning","created":"2021-10-07","cited_by_count":45},{"id":"2111.03289","title":"Improved Regret Analysis for Variance-Adaptive Linear Bandits and Horizon-Free Linear Mixture MDPs","created":"2021-11-05","cited_by_count":44},{"id":"2201.01985","title":"Jointly Efficient and Optimal Algorithms for Logistic Bandits","created":"2022-01-06","cited_by_count":41},{"id":"2302.10371","title":"Variance-Dependent Regret Bounds for Linear Bandits and Reinforcement Learning: Adaptivity and Computational Efficiency","created":"2023-02-21","cited_by_count":40},{"id":"2003.01971","title":"Corruption-Tolerant Gaussian Process Bandit Optimization","created":"2020-03-04","cited_by_count":34},{"id":"2106.02978","title":"Robust Stochastic Linear Contextual Bandits Under Adversarial Attacks","created":"2021-06-05","cited_by_count":33},{"id":"2212.05949","title":"Corruption-Robust Algorithms with Uncertainty Weighting for Nonlinear Contextual Bandits and Markov Decision Processes","created":"2022-12-12","cited_by_count":33},{"id":"2312.16730","title":"Foundations of Reinforcement Learning and Interactive Decision Making","created":"2023-12-27","cited_by_count":33},{"id":"1905.04654","title":"On the Performance of Thompson Sampling on Logistic Bandits","created":"2019-05-12","cited_by_count":32},{"id":"2311.09641","title":"RLHFPoison: Reward Poisoning Attack for Reinforcement Learning with Human Feedback in Large Language Models","created":"2023-11-16","cited_by_count":32},{"id":"2011.00819","title":"Self-Concordant Analysis of Generalized Linear Bandits with Forgetting","created":"2020-11-02","cited_by_count":29},{"id":"2407.13977","title":"A Unified Confidence Sequence for Generalized Linear Models, with Applications to Bandits","created":"2024-07-19","cited_by_count":29},{"id":"1509.07728","title":"Online Stochastic Linear Optimization under One-bit Feedback","created":"2015-09-25","cited_by_count":26},{"id":"2406.15568","title":"Robust Reinforcement Learning from Corrupted Human Feedback","created":"2024-06-21","cited_by_count":25},{"id":"2310.18554","title":"Improved Regret Bounds of (Multinomial) Logistic Bandits via Regret-to-Confidence-Set Conversion","created":"2023-10-28","cited_by_count":24},{"id":"2404.06831","title":"Generalized Linear Bandits with Limited Adaptivity","created":"2024-04-10","cited_by_count":22},{"id":"2110.12615","title":"Linear Contextual Bandits with Adversarial Corruptions","created":"2021-10-25","cited_by_count":21},{"id":"2402.06734","title":"Corruption Robust Offline Reinforcement Learning with Human Feedback","created":"2024-02-09","cited_by_count":20},{"id":"2405.09831","title":"Nearly Minimax Optimal Regret for Multinomial Logistic Bandit","created":"2024-05-16","cited_by_count":20},{"id":"2404.04102","title":"ROPO: Robust Preference Optimization for Large Language Models","created":"2024-04-05","cited_by_count":16},{"id":"2507.11847","title":"Generalized Linear Bandits: Almost Optimal Regret with One-Pass Update","created":"2025-07-16","cited_by_count":16},{"id":"2305.18543","title":"Robust Lipschitz Bandits to Adversarial Corruptions","created":"2023-05-29","cited_by_count":15},{"id":"2502.10020","title":"Improved Online Confidence Bounds for Multinomial Logistic Bandits","created":"2025-02-14","cited_by_count":15},{"id":"2002.07214","title":"Robust Stochastic Bandit Algorithms under Probabilistic Unbounded Adversarial Attack","created":"2020-02-17","cited_by_count":13},{"id":"2311.04402","title":"Likelihood Ratio Confidence Sets for Sequential Decision Making","created":"2023-11-08","cited_by_count":10},{"id":"2504.16555","title":"Confidence Sequences for Generalized Linear Models via Regret Analysis","created":"2025-04-23","cited_by_count":10},{"id":"2404.10776","title":"Nearly Optimal Algorithms for Contextual Dueling Bandits from Adversarial Feedback","created":"2024-04-16","cited_by_count":9},{"id":"2410.12713","title":"How Does Variance Shape the Regret in Contextual Bandits?","created":"2024-10-16","cited_by_count":9},{"id":"2410.01112","title":"Almost Free: Self-concordance in Natural Exponential Families and an Application to Bandits","created":"2024-10-01","cited_by_count":8},{"id":"2505.15694","title":"A Unified Theoretical Analysis of Private and Robust Offline Alignment: from RLHF to DPO","created":"2025-05-21","cited_by_count":8},{"id":"2410.07533","title":"Corruption-Robust Linear Bandits: Minimax Optimality and Gap-Dependent Misspecification","created":"2024-10-10","cited_by_count":7},{"id":"2502.14689","title":"Confidence Estimation via Sequential Likelihood Mixing","created":"2025-02-20","cited_by_count":7},{"id":"1709.08210","title":"Performance Bounds for Parameter Estimation under Misspecified Models: Fundamental findings and applications","created":"2017-09-24","cited_by_count":5},{"id":"2202.13603","title":"Optimal Online Generalized Linear Regression with Stochastic Noise and Its Application to Heteroscedastic Bandits","created":"2022-02-28","cited_by_count":5},{"id":"2503.03039","title":"LLM Misalignment via Adversarial RLHF Platforms","created":"2025-03-04","cited_by_count":5},{"id":"2502.17175","title":"Linear Bandits on Ellipsoids: Minimax Optimal Algorithms","created":"2025-02-24","cited_by_count":4},{"id":"2503.12020","title":"Variance-Dependent Regret Lower Bounds for Contextual Bandits","created":"2025-03-15","cited_by_count":4},{"id":"2506.03074","title":"GL-LowPopArt: A Nearly Instance-Wise Minimax-Optimal Estimator for Generalized Low-Rank Trace Regression","created":"2025-06-03","cited_by_count":4},{"id":"2511.09105","title":"Cost-Minimized Label-Flipping Poisoning Attack to LLM Alignment","created":"2025-11-12","cited_by_count":4},{"id":"2601.09825","title":"Eluder dimension: localise it!","created":"2026-01-14","cited_by_count":3}],"next_cursor":null}