Yu-Xiang Wang

Improved Regret in Stochastic Decision-Theoretic Online Learning under Differential Privacy ALT 2026 Rates for Offline Reinforcement Learning with Adaptively Collected Data L4DC 2025 Weak-to-Strong Jailbreaking on Large Language Models ICML 2025 Adapting to Linear Separable Subsets with Large-Margin in Differentially Private Learning ICML 2025 AKORN: Adaptive Knots generated Online for RegressioN splines ICML 2025 PROXSPARSE: REGULARIZED LEARNING OF SEMI-STRUCTURED SPARSITY MASKS FOR PRETRAINED LLMS ICML 2025 Adaptive Estimation and Learning under Temporal Distribution Shift ICML 2025 Adapting to Online Distribution Shifts in Deep Learning: A Black-Box Approach AISTATS 2025 Efficiently Identifying Watermarked Segments in Mixed-Source Texts ACL 2025 Permute-and-Flip: An optimally stable and watermarkable decoder for LLMs ICLR 2025 Improving Sample Efficiency of Model-Free Algorithms for Zero-Sum Markov Games ICML 2024 Differentially Private Bias-Term Fine-tuning of Foundation Models ICML 2024 Provable Robust Watermarking for AI-Generated Text ICLR 2024 Communication-Efficient Federated Non-Linear Bandit Optimization ICLR 2024 Tractable MCMC for Private Learning with Pure and Gaussian Differential Privacy ICLR 2024 CPR: Retrieval Augmented Generation for Copyright Protection CVPR 2024 Invisible Image Watermarks Are Provably Removable Using Generative AI NIPS 2024 Nonparametric Classification on Low Dimensional Manifolds using Overparameterized Convolutional Residual Networks NIPS 2024 Template-free Articulated Gaussian Splatting for Real-time Reposable Dynamic View Synthesis NIPS 2024 Differentially Private Reinforcement Learning with Self-Play NIPS 2024 Stable Minima Cannot Overfit in Univariate ReLU Networks: Generalization by Large Step Sizes NIPS 2024 NetworkGym: Reinforcement Learning Environments for Multi-Access Traffic Management in Network Simulation NIPS 2024 Online Feature Updates Improve Online (Generalized) Label Shift Adaptation NIPS 2024 Watermarking for Large Language Models ACL 2024 Pricing with Contextual Elasticity and Heteroscedastic Valuation ICML 2024 Neural Collapse meets Differential Privacy: Curious behaviors of NoisyGD with Near-Perfect Representation Learning ICML 2024 Near-Optimal Reinforcement Learning with Self-Play under Adaptivity Constraints ICML 2024 Privacy Profiles for Private Selection ICML 2024 Doubly Fair Dynamic Pricing AISTATS 2023 Posterior Sampling with Delayed Feedback for Reinforcement Learning with Linear Function Approximation NIPS 2023 Improving the Privacy and Practicality of Objective Perturbation for Differentially Private Linear Learners NIPS 2023 An Efficient and Robust Framework for Approximate Nearest Neighbor Search with Attribute Constraint NIPS 2023 Automatic Clipping: Differentially Private Deep Learning Made Easier and Stronger NIPS 2023 A Privacy-Friendly Approach to Data Valuation NIPS 2023 Offline Reinforcement Learning with Differential Privacy NIPS 2023 Online Label Shift: Optimal Dynamic Regret meets Practical Algorithms NIPS 2023 Generalized PTR: User-Friendly Recipes for Data-Adaptive Algorithms with Differential Privacy AISTATS 2023 Second Order Path Variationals in Non-Stationary Online Learning AISTATS 2023 Near-Optimal Differentially Private Reinforcement Learning AISTATS 2023 Offline Reinforcement Learning with Differentiable Function Approximation is Provably Efficient ICLR 2023 Near-Optimal Deployment Efficiency in Reward-Free Reinforcement Learning with Linear Function Approximation ICLR 2023 Deep Learning meets Nonparametric Regression: Are Weight-Decayed DNNs Locally Adaptive? ICLR 2023 Differentially Private Optimization on Large Model at Small Cost ICML 2023 Non-stationary Reinforcement Learning under General Function Approximation ICML 2023 Offline Reinforcement Learning with Closed-Form Policy Improvement Operators ICML 2023 Global Optimization with Parametric Function Approximation ICML 2023 Protecting Language Generation Models via Invisible Watermarking ICML 2023 Non-stationary Online Learning with Memory and Non-stochastic Control JMLR 2023 No-Regret Linear Bandits beyond Realizability UAI 2023 Private Prediction Strikes Back! Private Kernelized Nearest Neighbors with Individual Rényi Filter UAI 2023 Sample-Efficient Reinforcement Learning with loglog(T) Switching Cost ICML 2022 Adaptive Private-K-Selection with Adaptive K and Application to Multi-label PATE AISTATS 2022 Optimal Accounting of Differential Privacy via Characteristic Function AISTATS 2022 Non-stationary Online Learning with Memory and Non-stochastic Control AISTATS 2022 Optimal Dynamic Regret in Proper Online Learning with Strongly Convex Losses and Beyond AISTATS 2022 Towards Agnostic Feature-based Dynamic Pricing: Linear Policies vs Linear Valuation with Unknown Noise AISTATS 2022 Mixed Differential Privacy in Computer Vision CVPR 2022 Optimal Dynamic Regret in LQR Control NIPS 2022 Distillation-Resistant Watermarking for Model Protection in NLP EMNLP 2022 Near-optimal Offline Reinforcement Learning with Linear Representation: Leveraging Variance Information with Pessimism ICLR 2022 Differentially Private Linear Sketches: Efficient Implementations and Applications NIPS 2022 SeqPATE: Differentially Private Text Generation via Knowledge Distillation NIPS 2022 Offline stochastic shortest path: Learning, evaluation and towards optimality UAI 2022 Provably Confidential Language Modelling NAACL 2022 Towards Instance-Optimal Offline Reinforcement Learning with Pessimism NIPS 2021 An Optimal Reduction of TV-Denoising to Adaptive Online Learning AISTATS 2021 Optimal Dynamic Regret in Exp-Concave Online Learning COLT 2021 Near-Optimal Offline Reinforcement Learning via Double Variance Reduction NIPS 2021 Optimal Uniform OPE and Model-based Offline Reinforcement Learning in Time-Homogeneous, Reward-Free and Task-Agnostic Settings NIPS 2021 Revisiting Model-Agnostic Private Learning: Faster Rates and Active Learning JMLR 2021 Privately Publishable Per-instance Privacy NIPS 2021 Near-Optimal Provable Uniform Convergence in Offline Policy Evaluation for Reinforcement Learning AISTATS 2021 Logarithmic Regret in Feature-based Dynamic Pricing NIPS 2021 Revisiting Model-Agnostic Private Learning: Faster Rates and Active Learning AISTATS 2021 Private-kNN: Practical Differential Privacy for Computer Vision CVPR 2020 An end-to-end Differentially Private Latent Dirichlet Allocation Using a Spectral Algorithm ICML 2020 Adaptive Online Estimation of Piecewise Polynomial Trends NIPS 2020 Improving Sparse Vector Technique with Renyi Differential Privacy NIPS 2020 Domain Adaptation with Conditional Distribution Matching and Generalized Label Shift NIPS 2020 Asymptotically Efficient Off-Policy Evaluation for Tabular Reinforcement Learning AISTATS 2020 Poission Subsampled Rényi Differential Privacy ICML 2019 Provably Efficient Q-Learning with Low Switching Cost NIPS 2019 Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting NIPS 2019 Online Forecasting of Total-Variation-bounded Sequences NIPS 2019 Subsampled Renyi Differential Privacy and Analytical Moments Accountant AISTATS 2019 A Higher-Order Kolmogorov-Smirnov Test AISTATS 2019 Imitation-Regularized Offline Learning AISTATS 2019 Towards Optimal Off-Policy Evaluation for Reinforcement Learning with Marginalized Importance Sampling NIPS 2019 ProxQuant: Quantized Neural Networks via Proximal Operators ICLR 2019 Detecting and Correcting for Label Shift with Black Box Predictors ICML 2018 signSGD: Compressed Optimisation for Non-Convex Problems ICML 2018 Improving the Gaussian Mechanism for Differential Privacy: Analytical Calibration and Optimal Denoising ICML 2018 Higher-Order Total Variation Classes on Grids: Minimax Theory and Trend Filtering Methods NIPS 2017 Attributing Hacks AISTATS 2017 Optimal and Adaptive Off-policy Evaluation in Contextual Bandits ICML 2017 Learning with Differential Privacy: Stability, Learnability and the Sufficiency and Necessity of ERM Principle JMLR 2016 Noisy Sparse Subspace Clustering JMLR 2016 Graph Connectivity in Noisy Sparse Subspace Clustering AISTATS 2016 Graph Sparsification Approaches for Laplacian Smoothing AISTATS 2016 Parallel and Distributed Block-Coordinate Frank-Wolfe Algorithms ICML 2016 Total Variation Classes Beyond 1d: Minimax Rates, and the Limitations of Linear Smoothers NIPS 2016 Trend Filtering on Graphs JMLR 2016 A Deterministic Analysis of Noisy Sparse Subspace Clustering for Dimensionality-reduced Data ICML 2015 Differentially private subspace clustering NIPS 2015 Privacy for Free: Posterior Sampling and Stochastic Gradient Monte Carlo ICML 2015 Trend Filtering on Graphs AISTATS 2015 The Falling Factorial Basis and Its Statistical Applications ICML 2014 Noisy Sparse Subspace Clustering ICML 2013 Provable Subspace Clustering: When LRR meets SSC NIPS 2013