YW
Yu-Xiang Wang
cs.LGstat.MLcs.AIcs.CRmath.OCecon.EMcs.CVcs.DCcs.HCCOVID-19
On Valency
published · living versionsW_y4jmtctj·v1 · currentpublished
Optimal and Adaptive Off-policy Evaluation in Contextual Bandits
with Alekh Agarwal, Miroslav Dudik
1 version
Preprints & journals
63 papers in the corpus · 2013–2025Not-a-Bandit: Provably No-Regret Drafter Selection in Speculative Decoding for LLMs2510.20064v2 · Hongyi Liu, Jiaji Huang, Zhen Jia et al.2025 · 0 citationsarXiv
Generalization Below the Edge of Stability: The Role of Data Geometry2510.18120v3 · Tongtong Liang, Alexander Cloninger, Rahul Parhi et al.2025 · 0 citationsarXiv
DPCheatSheet: Using Worked and Erroneous LLM-usage Examples to Scaffold Differential Privacy Implementation2509.12590v1 · Shao-Yu Chu, Yuhe Tian, Yu-Xiang Wang et al.2025 · 0 citationsarXiv
DRWKV: Focusing on Object Edges for Low-Light Image Enhancement2507.18594v3 · Xuecheng Bai, Yuxiang Wang, Boyu Hu et al.2025 · 2 citationsarXiv
Stable Minima of ReLU Neural Networks Suffer from the Curse of Dimensionality: The Neural Shattering Phenomenon2506.20779v4 · Tongtong Liang, Dan Qiao, Yu-Xiang Wang et al.2025 · 0 citationsarXiv
MGDFIS: Multi-scale Global-detail Feature Integration Strategy for Small Object Detection2506.12697v4 · Yuxiang Wang, Xuecheng Bai, Chuanzhi Xu et al.2025 · 0 citationsarXiv
Purifying Approximate Differential Privacy with Randomized Post-processing2503.21071v2 · Yingyu Lin, Erchi Wang, Yi-An Ma et al.2025 · 0 citationsarXiv
Improved Regret in Stochastic Decision-Theoretic Online Learning under Differential Privacy2502.10997v2 · Ruihan Wu, Yu-Xiang Wang2025 · 0 citationsarXiv
Dynamic Pricing with Adversarially-Censored Demands2502.06168v2 · Jianyu Xu, Yining Wang, Xi Chen et al.2025 · 0 citationsarXiv
TempCompass: Do Video LLMs Really Understand Videos?2403.00476v3 · Yuanxin Liu, Shicheng Li, Yi Liu et al.2024 · 45 citationsarXiv
Pricing with Contextual Elasticity and Heteroscedastic Valuation2312.15999v1 · Jianyu Xu, Yu-Xiang Wang2023 · 0 citationsarXiv
Communication-Efficient Federated Non-Linear Bandit Optimization2311.01695v1 · Chuanhao Li, Chong Liu, Yu-Xiang Wang2023 · 1 citationarXiv
Advancing Differential Privacy: Where We Are Now and Future Directions for Real-World Deployment2304.06929v2 · Rachel Cummings, Damien Desfontaines, David Evans et al.2023 · 52 citationsarXiv
Improved Differentially Private Regression via Gradient Boosting2303.03451v2 · Shuai Tang, Sergul Aydore, Michael Kearns et al.2023 · 1 citationarXiv
No-Regret Linear Bandits beyond Realizability2302.13252v2 · Chong Liu, Ming Yin, Yu-Xiang Wang2023 · 0 citationsProceedings of the 39th Conference on Uncertainty in Artificial Intelligence, PMLR 216:1294-1303, 2023
Logarithmic Switching Cost in Reinforcement Learning beyond Linear MDPs2302.12456v1 · Dan Qiao, Ming Yin, Yu-Xiang Wang2023 · 0 citationsarXiv
Global Optimization with Parametric Function Approximation2211.09100v3 · Chong Liu, Yu-Xiang Wang2022 · 1 citationProceedings of the 40th International Conference on Machine Learning, PMLR 202:22113-22136, 2023
Random Walk-based Community Key-members Search over Large Graphs2210.17403v5 · Yuxiang Wang, Yuyang Zhao, Xiaoliang Xu et al.2022 · 2 citationsarXiv
Near-Optimal Deployment Efficiency in Reward-Free Reinforcement Learning with Linear Function Approximation2210.00701v2 · Dan Qiao, Yu-Xiang Wang2022 · 1 citationarXiv
Doubly Fair Dynamic Pricing2209.11837v1 · Jianyu Xu, Dan Qiao, Yu-Xiang Wang2022 · 2 citationsarXiv
Offline Stochastic Shortest Path: Learning, Evaluation and Towards Optimality2206.04921v1 · Ming Yin, Wenjing Chen, Mengdi Wang et al.2022 · 0 citationsarXiv
Provably Confidential Language Modelling2205.01863v2 · Xuandong Zhao, Lei Li, Yu-Xiang Wang2022 · 13 citationsarXiv
Second Order Path Variationals in Non-Stationary Online Learning2205.01921v2 · Dheeraj Baby, Yu-Xiang Wang2022 · 0 citationsarXiv
Evaluation of individual and ensemble probabilistic forecasts of COVID-19 mortality in the United States.35394862 · Cramer, Estee Y, Ray, Evan L, Lopez, Velma K et al.2022 · 309 citationsProceedings of the National Academy of Sciences of the United States of America. 2022;119(15):e2113561119
Sample-Efficient Reinforcement Learning with loglog(T) Switching Cost2202.06385v2 · Dan Qiao, Ming Yin, Ming Min et al.2022 · 3 citationsarXiv
Towards Agnostic Feature-based Dynamic Pricing: Linear Policies vs Linear Valuation with Unknown Noise2201.11341v2 · Jianyu Xu, Yu-Xiang Wang2022 · 4 citationsarXiv
Optimal Dynamic Regret in Proper Online Learning with Strongly Convex Losses and Beyond2201.08905v1 · Dheeraj Baby, Yu-Xiang Wang2022 · 5 citationsarXiv
Towards Instance-Optimal Offline Reinforcement Learning with Pessimism2110.08695v1 · Ming Yin, Yu-Xiang Wang2021 · 7 citationsarXiv
Optimal Uniform OPE and Model-based Offline Reinforcement Learning in Time-Homogeneous, Reward-Free and Task-Agnostic Settings2105.06029v3 · Ming Yin, Yu-Xiang Wang2021 · 1 citationarXiv
Optimal Dynamic Regret in Exp-Concave Online Learning2104.11824v2 · Dheeraj Baby, Yu-Xiang Wang2021 · 10 citationsarXiv
Logarithmic Regret in Feature-based Dynamic Pricing2102.10221v2 · Jianyu Xu, Yu-Xiang Wang2021 · 7 citationsarXiv
Non-stationary Online Learning with Memory and Non-stochastic Control2102.03758v4 · Peng Zhao, Yu-Hu Yan, Yu-Xiang Wang et al.2021 · 12 citationsJournal of Machine Learning Research, 2023
Near-Optimal Offline Reinforcement Learning via Double Variance Reduction2102.01748v1 · Ming Yin, Yu Bai, Yu-Xiang Wang2021 · 22 citationsarXiv
An Optimal Reduction of TV-Denoising to Adaptive Online Learning2101.09438v2 · Dheeraj Baby, Xuandong Zhao, Yu-Xiang Wang2021 · 2 citationsarXiv
Inter-Series Attention Model for COVID-19 Forecasting2010.13006v2 · Xiaoyong Jin, Yu-Xiang Wang, Xifeng Yan2020 · 42 citationsarXiv
Adaptive Online Estimation of Piecewise Polynomial Trends2010.00073v1 · Dheeraj Baby, Yu-Xiang Wang2020 · 3 citationsarXiv
Near-Optimal Provable Uniform Convergence in Offline Policy Evaluation for Reinforcement Learning2007.03760v2 · Ming Yin, Yu Bai, Yu-Xiang Wang2020 · 24 citationsarXiv
Bullseye Polytope: A Scalable Clean-Label Poisoning Attack with Improved Transferability2005.00191v3 · Hojjat Aghakhani, Dongyu Meng, Yu-Xiang Wang et al.2020 · 79 citationsarXiv
Domain Adaptation with Conditional Distribution Matching and Generalized Label Shift2003.04475v3 · Remi Tachet, Han Zhao, Yu-Xiang Wang et al.2020 · 85 citationsarXiv
Asymptotically Efficient Off-Policy Evaluation for Tabular Reinforcement Learning2001.10742v1 · Ming Yin, Yu-Xiang Wang2020 · 26 citationsInternational Conference on Artificial Intelligence and Statistics, 108 (2020) 3948-3958
Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting1907.00235v3 · Shiyang Li, Xiaoyong Jin, Yao Xuan et al.2019 · 1,327 citationsarXiv
Towards Optimal Off-Policy Evaluation for Reinforcement Learning with Marginalized Importance Sampling1906.03393v4 · Tengyang Xie, Yifei Ma, Yu-Xiang Wang2019 · 70 citationsarXiv
Doubly Robust Crowdsourcing1906.08591v2 · Chong Liu, Yu-Xiang Wang2019 · 1 citationJournal of Artificial Intelligence Research 73 (2022) 209-229
Provably Efficient Q-Learning with Low Switching Cost1905.12849v3 · Yu Bai, Tengyang Xie, Nan Jiang et al.2019 · 28 citationsarXiv
Imitation-Regularized Offline Learning1901.04723v1 · Yifei Ma, Yu-Xiang Wang, Balakrishnan Narayanaswamy2019 · 10 citationsarXiv
ProxQuant: Quantized Neural Networks via Proximal Operators1810.00861v3 · Yu Bai, Yu-Xiang Wang, Edo Liberty2018 · 76 citationsarXiv
Patch-Based Image Hallucination for Super Resolution with Detail Reconstruction from Similar Sample Images1806.00874v1 · Chieh-Chi Kao, Yuxiang Wang, Jonathan Waltman et al.2018 · 6 citationsarXiv
An end-to-end Differentially Private Latent Dirichlet Allocation Using a Spectral Algorithm1805.10341v3 · Christopher DeCarolis, Mukul Ram, Seyed A. Esmaeili et al.2018 · 4 citationsarXiv
Improving the Gaussian Mechanism for Differential Privacy: Analytical Calibration and Optimal Denoising1805.06530v2 · Borja Balle, Yu-Xiang Wang2018 · 230 citationsarXiv
signSGD: Compressed Optimisation for Non-Convex Problems1802.04434v3 · Jeremy Bernstein, Yu-Xiang Wang, Kamyar Azizzadenesheli et al.2018 · 541 citationsarXiv
Career total: 116 works. 63 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.