Ambuj Tewari

A Theoretical Framework for Partially-Observed Reward States in RLHF ICLR 2025 Learning Infinite-Horizon Average-Reward Linear Mixture MDPs of Bounded Span AISTATS 2025 On the Benefits of Active Data Collection in Operator Learning ICML 2025 Generation through the lens of learning theory COLT 2025 A Computationally Efficient Algorithm for Infinite-Horizon Average-Reward Linear MDPs ICML 2025 Leveraging Offline Data in Linear Latent Contextual Bandits ICML 2025 A Unified Theory of Supervised Online Learnability ALT 2025 Reinforcement Learning for Infinite-Horizon Average-Reward Linear MDPs via Approximation by Discounted-Reward MDPs AISTATS 2025 The Complexity of Sequential Prediction in Dynamical Systems L4DC 2025 A Primal-Dual Algorithm for Offline Constrained Reinforcement Learning with Linear MDPs ICML 2024 Variational Inference with Coverage Guarantees in Simulation-Based Inference ICML 2024 A Characterization of Multioutput Learnability JMLR 2024 On the Computational Complexity of Private High-dimensional Model Selection NIPS 2024 Online Classification with Predictions NIPS 2024 Smoothed Online Classification can be Harder than Batch Classification NIPS 2024 A Primal-Dual-Critic Algorithm for Offline Constrained Reinforcement Learning AISTATS 2024 Sequence Length Independent Norm-Based Generalization Bounds for Transformers AISTATS 2024 Offline Policy Evaluation and Optimization Under Confounding AISTATS 2024 Conformal Contextual Robust Optimization AISTATS 2024 Multiclass Online Learnability under Bandit Feedback ALT 2024 Online Infinite-Dimensional Regression: Learning Linear Operators ALT 2024 Apple Tasting: Combinatorial Dimensions and Minimax Rates COLT 2024 Online Learning with Set-valued Feedback COLT 2024 Sample Efficient Myopic Exploration Through Multitask Reinforcement Learning with Diverse Tasks ICLR 2024 On Proper Learnability between Average- and Worst-case Robustness NIPS 2023 Thompson Sampling for High-Dimensional Sparse Linear Contextual Bandits ICML 2023 An Optimization-based Algorithm for Non-stationary Kernel Bandits without Prior Knowledge AISTATS 2023 On the Learnability of Multilabel Ranking NIPS 2023 Learning Mixtures of Markov Chains and MDPs ICML 2023 Learning in online MDPs: is there a price for handling the communicating case? UAI 2023 Multiclass Online Learning and Uniform Convergence COLT 2023 Online Agnostic Multiclass Boosting NIPS 2022 Weighted Gaussian Process Bandits for Non-stationary Environments AISTATS 2022 Efficient Reinforcement Learning with Prior Causal Knowledge CLEAR 2022 Adaptive Sampling for Discovery NIPS 2022 On the Statistical Benefits of Curriculum Learning ICML 2022 Balancing adaptability and non-exploitability in repeated games UAI 2022 Low-Rank Generalized Linear Bandit Problems AISTATS 2021 Decision Making Problems with Funnel Structure: A Multi-Task Learning Approach with Application to Email Marketing Campaigns AISTATS 2021 Thompson sampling for Markov games with piecewise stationary opponent policies UAI 2021 Causal Bandits with Unknown Graph Structure NIPS 2021 Representation Learning Beyond Linear Prediction Functions NIPS 2021 Randomized Exploration for Non-Stationary Stochastic Linear Bandits UAI 2020 On the Equivalence between Online and Private Learnability beyond Binary Classification NIPS 2020 Reinforcement Learning in Factored MDPs: Oracle-Efficient Algorithms and Tighter Regret Bounds for the Non-Episodic Setting NIPS 2020 TorsionNet: A Reinforcement Learning Approach to Sequential Conformer Search NIPS 2020 Sample Complexity of Reinforcement Learning using Linearly Combined Model Ensembles AISTATS 2020 Regret Analysis of Bandit Problems with Causal Background Knowledge UAI 2020 What You See May Not Be What You Get: UCB Bandit Algorithms Robust to $\varepsilon$-Contamination UAI 2020 No-regret Exploration in Contextual Reinforcement Learning UAI 2020 Online Multiclass Boosting with Bandit Feedback AISTATS 2019 Generalization Bounds in the Predict-then-Optimize Framework NIPS 2019 On the Optimality of Perturbations in Stochastic and Adversarial Multi-armed Bandit Problems NIPS 2019 Regret Bounds for Thompson Sampling in Episodic Restless Bandit Problems NIPS 2019 Online Learning via the Differential Privacy Lens NIPS 2019 Cost-Sensitive Learning with Noisy Labels JMLR 2018 Beyond the Hazard Rate: More Perturbation Algorithms for Adversarial Multi-armed Bandits JMLR 2018 Markov Decision Processes with Continuous Side Information ALT 2018 But How Does It Work in Theory? Linear SVM with Random Features NIPS 2018 Active Learning for Non-Parametric Regression Using Purely Random Trees NIPS 2018 Online Boosting Algorithms for Multi-label Ranking AISTATS 2018 Action Centered Contextual Bandits NIPS 2017 Online Learning to Rank with Top-k Feedback JMLR 2017 Online multiclass boosting NIPS 2017 On Structural Properties of MDPs that Bound Loss Due to Shallow Planning IJCAI 2016 Mixture Proportion Estimation via Kernel Embeddings of Distributions ICML 2016 Phased Exploration with Greedy Exploitation in Stochastic Combinatorial Partial Monitoring Games NIPS 2016 Predtron: A Family of Online Algorithms for General Prediction Problems NIPS 2015 Online Ranking with Top-1 Feedback AISTATS 2015 Online Learning via Sequential Complexities JMLR 2015 Fighting Bandits with a New Kind of Smoothness NIPS 2015 Generalization error bounds for learning to rank: Does the length of document lists matter? ICML 2015 Alternating Minimization for Regression Problems with Vector-valued Outputs NIPS 2015 Convex Calibrated Surrogates for Hierarchical Classification ICML 2015 Online Linear Optimization via Smoothing COLT 2014 Prediction and Clustering in Signed Networks: A Local to Global Perspective JMLR 2014 On Iterative Hard Thresholding Methods for High-dimensional M-Estimation NIPS 2014 Learning with Noisy Labels NIPS 2013 Convex Calibrated Surrogates for Low-Rank Loss Matrices with Applications to Subset Ranking Losses NIPS 2013 On Robust Estimation of High Dimensional Generalized Linear Models IJCAI 2013 Perturbation based Large Margin Approach for Ranking AISTATS 2012 Regularization Techniques for Learning with Matrices JMLR 2012 Feature Clustering for Accelerating Parallel Coordinate Descent NIPS 2012 Online Learning: Beyond Regret COLT 2011 Improved Regret Guarantees for Online Smooth Convex Optimization with Bandit Feedback AISTATS 2011 Stochastic Methods for -regularized Loss Minimization JMLR 2011 On NDCG Consistency of Listwise Ranking Methods AISTATS 2011 Greedy Algorithms for Structurally Constrained High Dimensional Problems NIPS 2011 On the Universality of Online Mirror Descent NIPS 2011 Online Learning: Stochastic, Constrained, and Smoothed Adversaries NIPS 2011 Orthogonal Matching Pursuit with Replacement NIPS 2011 Nearest Neighbor based Greedy Coordinate Descent NIPS 2011 Complexity-Based Approach to Calibration with Checking Rules COLT 2011 Learning Exponential Families in High-Dimensions: Strong Convexity and Sparsity AISTATS 2010 Online Learning: Random Averages, Combinatorial Parameters, and Learnability NIPS 2010 Smoothness, Low Noise and Fast Rates NIPS 2010 On the Complexity of Linear Prediction: Risk Bounds, Margin Bounds, and Regularization NIPS 2008 On the Generalization Ability of Online Strongly Convex Programming Algorithms NIPS 2008 Sparseness vs Estimating Conditional Probabilities: Some Asymptotic Results JMLR 2007 Optimistic Linear Programming gives Logarithmic Regret for Irreducible MDPs NIPS 2007 On the Consistency of Multiclass Classification Methods JMLR 2007 Sample Complexity of Policy Search with Known Dynamics NIPS 2006