Wu, Steven

73 publications

ICLR 2026 All Roads Lead to Likelihood: The Value of Reinforcement Learning in Fine-Tuning Gokul Swamy, Sanjiban Choudhury, Wen Sun, Steven Wu, Drew Bagnell

ICLR 2026 Dimension-Free Decision Calibration for Nonlinear Loss Functions Jingwu Tang, Jiayun Wu, Steven Wu, Jiahao Zhang

ICLR 2026 Doubly-Robust LLM-as-a-Judge: Externally Valid Estimation with Imperfect Personas Luke Guerdan, Justin Whitehouse, Kimberly Truong, Ken Holstein, Steven Wu

ICLR 2026 From Curiosity to Caution: Mitigating Reward Hacking for Best-of-$n$ with Pessimism Zhuohao Yu, Steven Wu, Adam Block

TMLR 2026 Incentive-Aware Synthetic Control: Accurate Counterfactual Estimation via Incentivized Exploration Dung Daniel Ngo, Keegan Harris, Anish Agarwal, Vasilis Syrgkanis, Steven Wu

ICLR 2026 Nearly-Optimal Bandit Learning in Stackelberg Games with Side Information Maria Florina Balcan, Martino Bernasconi, Matteo Castiglioni, Andrea Celli, Keegan Harris, Steven Wu

ICLR 2026 Optimizing Canaries for Privacy Auditing with Metagradient Descent Matteo Boglioni, Terrance Liu, Andrew Ilyas, Steven Wu

NeurIPS 2025 Discretization-Free Multicalibration Through Loss Minimization over Tree Ensembles Hongyi Henry Jin, Zijun Ding, Dung Daniel Ngo, Steven Wu

ICML 2025 Kandinsky Conformal Prediction: Beyond Class- and Covariate-Conditional Coverage Konstantina Bairaktari, Jiayun Wu, Steven Wu

ICML 2025 Leveraging Model Guidance to Extract Training Data from Personalized Diffusion Models Xiaoyu Wu, Jiaru Zhang, Steven Wu

UAI 2025 Multi-Group Uncertainty Quantification for Long-Form Text Generation Terrance Liu, Steven Wu

ICLR 2025 Reconciling Model Multiplicity for Downstream Decision Making Ally Yalei Du, Dung Daniel Ngo, Steven Wu

NeurIPS 2025 Unlearned but Not Forgotten: Data Extraction After Exact Unlearning in LLM Xiaoyu Wu, Yifei Pang, Terrance Liu, Steven Wu

ICLR 2025 Unlearning or Obfuscating? Jogging the Memory of Unlearned LLMs via Benign Relearning Shengyuan Hu, Yiwei Fu, Steven Wu, Virginia Smith

ICLR 2025 Utility-Directed Conformal Prediction: A Decision-Aware Framework for Actionable Uncertainty Quantification Santiago Cortes-Gomez, Carlos Miguel Patiño, Yewon Byun, Steven Wu, Eric Horvitz, Bryan Wilder

NeurIPS 2025 Validating LLM-as-a-Judge Systems Under Rating Indeterminacy Luke Guerdan, Solon Barocas, Ken Holstein, Hanna Wallach, Steven Wu, Alexandra Chouldechova

ICML 2024 A Minimaximalist Approach to Reinforcement Learning from Human Feedback Gokul Swamy, Christoph Dann, Rahul Kidambi, Steven Wu, Alekh Agarwal

NeurIPSW 2024 A New Approach to Generate Individual Level Data of Walled Garden Platforms: Linear Programming Reconstruction Yifei Pang, Sreenidhi Ganachari, Yuan Yuan, Steven Wu, Xiaojing Dong, Jin Xu, Zhenyu Yan

ICLR 2024 Differentially Private SGD Without Clipping Bias: An Error-Feedback Approach Xinwei Zhang, Zhiqi Bu, Steven Wu, Mingyi Hong

ICML 2024 Hybrid Inverse Reinforcement Learning Juntao Ren, Gokul Swamy, Steven Wu, Drew Bagnell, Sanjiban Choudhury

NeurIPSW 2024 Jogging the Memory of Unlearned LLMs Through Targeted Relearning Attacks Shengyuan Hu, Yiwei Fu, Steven Wu, Virginia Smith

ICMLW 2024 Jogging the Memory of Unlearned Models Through Targeted Relearning Attacks Shengyuan Hu, Yiwei Fu, Steven Wu, Virginia Smith

ICML 2024 Membership Inference Attacks on Diffusion Models via Quantile Regression Shuai Tang, Steven Wu, Sergul Aydore, Michael Kearns, Aaron Roth

ICMLW 2024 Multi-Agent Imitation Learning: Value Is Easy, Regret Is Hard Jingwu Tang, Gokul Swamy, Fei Fang, Steven Wu

ICMLW 2024 Multi-Agent Imitation Learning: Value Is Easy, Regret Is Hard Jingwu Tang, Gokul Swamy, Fei Fang, Steven Wu

ICML 2024 Predictive Performance Comparison of Decision Policies Under Confounding Luke Guerdan, Amanda Lee Coston, Ken Holstein, Steven Wu

TMLR 2024 The Disagreement Problem in Explainable Machine Learning: A Practitioner’s Perspective Satyapriya Krishna, Tessa Han, Alex Gu, Steven Wu, Shahin Jabbari, Himabindu Lakkaraju

ICMLW 2023 Complementing a Policy with a Different Observation Space Gokul Swamy, Sanjiban Choudhury, Drew Bagnell, Steven Wu

ICML 2023 Fully-Adaptive Composition in Differential Privacy Justin Whitehouse, Aaditya Ramdas, Ryan Rogers, Steven Wu

ICML 2023 Generating Private Synthetic Data with Genetic Algorithms Terrance Liu, Jingwu Tang, Giuseppe Vietri, Steven Wu

ICML 2023 Inverse Reinforcement Learning Without Reinforcement Learning Gokul Swamy, David Wu, Sanjiban Choudhury, Drew Bagnell, Steven Wu

ICMLW 2023 Learning Shared Safety Constraints from Multi-Task Demonstrations Konwoo Kim, Gokul Swamy, Zuxin Liu, Ding Zhao, Sanjiban Choudhury, Steven Wu

ICMLW 2023 Learning Shared Safety Constraints from Multi-Task Demonstrations Konwoo Kim, Gokul Swamy, Zuxin Liu, Ding Zhao, Sanjiban Choudhury, Steven Wu

NeurIPSW 2023 Membership Inference Attack on Diffusion Models via Quantile Regression Steven Wu, Shuai Tang, Sergul Aydore, Michael Kearns, Aaron Roth

ICLR 2023 Meta-Learning in Games Keegan Harris, Ioannis Anagnostides, Gabriele Farina, Mikhail Khodak, Steven Wu, Tuomas Sandholm

ICML 2023 Nonparametric Extensions of Randomized Response for Private Confidence Sets Ian Waudby-Smith, Steven Wu, Aaditya Ramdas

NeurIPSW 2023 Policy Comparison Under Unmeasured Confounding Luke Guerdan, Amanda Coston, Steven Wu, Ken Holstein

TMLR 2023 Private Multi-Task Learning: Formulation and Applications to Federated Learning Shengyuan Hu, Steven Wu, Virginia Smith

AISTATS 2023 Reinforcement Learning with Stepwise Fairness Constraints Zhun Deng, He Sun, Steven Wu, Linjun Zhang, David Parkes

NeurIPSW 2023 Stackelberg Games with Side Information Keegan Harris, Steven Wu, Maria Florina Balcan

ICMLW 2023 Strategic Apple Tasting Keegan Harris, Chara Podimata, Steven Wu

ICMLW 2023 Strategic Apple Tasting Keegan Harris, Chara Podimata, Steven Wu

ICMLW 2023 Strategyproof Decision-Making in Panel Data Settings and Beyond Keegan Harris, Anish Agarwal, Chara Podimata, Steven Wu

ICML 2022 Causal Imitation Learning Under Temporally Correlated Noise Gokul Swamy, Sanjiban Choudhury, Drew Bagnell, Steven Wu

NeurIPSW 2022 Choosing Public Datasets for Private Machine Learning via Gradient Subspace Distance Xin Gu, Gautam Kamath, Steven Wu

ICML 2022 Constrained Variational Policy Optimization for Safe Reinforcement Learning Zuxin Liu, Zhepeng Cen, Vladislav Isenbaev, Wei Liu, Steven Wu, Bo Li, Ding Zhao

NeurIPSW 2022 Counterfactual Decision Support Under Treatment-Conditional Outcome Measurement Error Luke Guerdan, Amanda Lee Coston, Ken Holstein, Steven Wu

NeurIPSW 2022 Differentially Private Gradient Boosting on Linear Learners for Tabular Data Saeyoung Rho, Cedric Archambeau, Sergul Aydore, Beyza Ermis, Michael Kearns, Aaron Roth, Shuai Tang, Yu-Xiang Wang, Steven Wu

ICML 2022 Improved Regret for Differentially Private Exploration in Linear MDP Dung Daniel T Ngo, Giuseppe Vietri, Steven Wu

ICML 2022 Information Discrepancy in Strategic Learning Yahav Bechavod, Chara Podimata, Steven Wu, Juba Ziani

ICML 2022 Personalization Improves Privacy-Accuracy Tradeoffs in Federated Learning Alberto Bietti, Chen-Yu Wei, Miroslav Dudik, John Langford, Steven Wu

ICML 2022 Strategic Instrumental Variable Regression: Recovering Causal Relationships from Strategic Responses Keegan Harris, Dung Daniel T Ngo, Logan Stapleton, Hoda Heidari, Steven Wu

NeurIPSW 2022 Strategy-Aware Contextual Bandits Keegan Harris, Chara Podimata, Steven Wu

NeurIPSW 2022 Strategy-Aware Contextual Bandits Keegan Harris, Chara Podimata, Steven Wu

NeurIPSW 2022 Strategy-Aware Contextual Bandits Keegan Harris, Chara Podimata, Steven Wu

ICLRW 2022 Towards Differentially Private Query Release for Hierarchical Data Terrance Liu, Steven Wu

ICML 2022 Understanding Clipping for Federated Learning: Convergence and Client-Level Differential Privacy Xinwei Zhang, Xiangyi Chen, Mingyi Hong, Steven Wu, Jinfeng Yi

AISTATS 2021 Gaming Helps! Learning from Strategic Interactions in Natural Dynamics Yahav Bechavod, Katrina Ligett, Steven Wu, Juba Ziani

AISTATS 2021 Learn to Expect the Unexpected: Probably Approximately Correct Domain Generalization Vikas Garg, Adam Tauman Kalai, Katrina Ligett, Steven Wu

ICLR 2021 Bypassing the Ambient Dimension: Private SGD with Gradient Subspace Identification Yingxue Zhou, Steven Wu, Arindam Banerjee

ICML 2021 Incentivizing Compliance with Algorithmic Instruments Dung Daniel T Ngo, Logan Stapleton, Vasilis Syrgkanis, Steven Wu

NeurIPSW 2021 Iterative Methods for Private Synthetic Data: Unifying Framework and New Methods Terrance Liu, Giuseppe Vietri, Steven Wu

ICML 2021 Leveraging Public Data for Practical Private Query Release Terrance Liu, Giuseppe Vietri, Thomas Steinke, Jonathan Ullman, Steven Wu

ICML 2021 Of Moments and Matching: A Game-Theoretic Framework for Closing the Imitation Gap Gokul Swamy, Sanjiban Choudhury, J. Andrew Bagnell, Steven Wu

ICLR 2021 Private Post-GAN Boosting Marcel Neunhoeffer, Steven Wu, Cynthia Dwork

ICML 2021 Towards the Unification and Robustness of Perturbation and Gradient Based Explanations Sushant Agarwal, Shahin Jabbari, Chirag Agarwal, Sohini Upadhyay, Steven Wu, Himabindu Lakkaraju

NeurIPSW 2021 What Would the Expert $do(\cdot)$?: Causal Imitation Learning Gokul Swamy, Sanjiban Choudhury, Drew Bagnell, Steven Wu

ICML 2020 New Oracle-Efficient Algorithms for Private Synthetic Data Release Giuseppe Vietri, Grace Tian, Mark Bun, Thomas Steinke, Steven Wu

ICML 2020 Oracle Efficient Private Non-Convex Optimization Seth Neel, Aaron Roth, Giuseppe Vietri, Steven Wu

ICML 2020 Private Query Release Assisted by Public Data Raef Bassily, Albert Cheu, Shay Moran, Aleksandar Nikolov, Jonathan Ullman, Steven Wu

ICML 2020 Private Reinforcement Learning with PAC and Regret Guarantees Giuseppe Vietri, Borja Balle, Akshay Krishnamurthy, Steven Wu

ICML 2020 Privately Learning Markov Random Fields Huanyu Zhang, Gautam Kamath, Janardhan Kulkarni, Steven Wu

ICML 2020 Structured Linear Contextual Bandits: A Sharp and Geometric Smoothed Analysis Vidyashankar Sivakumar, Steven Wu, Arindam Banerjee