ZW
Zhiwei Steven Wu
cs.LGstat.MLcs.CRcs.GTcs.DScs.CYcs.AIcs.HCstat.MEmath.ST
On Valency
published · living versionsW_gznmqr39·v1 · currentpublished
Preprints & journals
144 papers in the corpus · 2014–2026Optimizing Canaries for Privacy Auditing with Metagradient Descent2507.15836v2 · Matteo Boglioni, Terrance Liu, Andrew Ilyas et al.2025 · 0 citationsInternational Conference on Learning Representations (ICLR) 2026, pp. 92994-93013
Many AI analysts, one dataset: Navigating the agentic data science multiverse.42446982 · Bertran, Martin, Fogliato, Riccardo, Wu, Zhiwei Steven2026 · 0 citationsProceedings of the National Academy of Sciences of the United States of America. 2026;123(29):e2606495123
Membership Inference Attacks for Unseen Classes2506.06488v3 · Pratiksha Thaker, Neil Kale, Zhiwei Steven Wu et al.2025 · 0 citationsarXiv
SEVRA-BENCH: Social Engineering of Vulnerabilities in Review Agents2606.13757v2 · Rui Melo, Riccardo Fogliato, Sean Zhou et al.2026 · 0 citationsarXiv
Nearly-Optimal Bandit Learning in Stackelberg Games with Side Information2502.00204v3 · Maria-Florina Balcan, Martino Bernasconi, Matteo Castiglioni et al.2025 · 0 citationsarXiv
Incentivizing Exploration with Selective Data Disclosure1811.06026v8 · Nicole Immorlica, Jieming Mao, Aleksandrs Slivkins et al.2018 · 18 citationsarXiv
Many AI Analysts, One Dataset: Navigating the Agentic Data Science Multiverse2602.18710v2 · Martin Bertran, Riccardo Fogliato, Zhiwei Steven Wu2026 · 0 citationsarXiv
Doubly-Robust LLM-as-a-Judge: Externally Valid Estimation with Imperfect Personas2509.22957v2 · Luke Guerdan, Justin Whitehouse, Kimberly Truong et al.2025 · 0 citationsarXiv
Incentive-Aware Synthetic Control: Accurate Counterfactual Estimation via Incentivized Exploration2312.16307v3 · Daniel Ngo, Keegan Harris, Anish Agarwal et al.2023 · 0 citationsarXiv
Improving the Convergence of Private Shuffled Gradient Methods with Public Data2502.03652v2 · Shuli Jiang, Pranay Sharma, Zhiwei Steven Wu et al.2025 · 0 citationsarXiv
MarkTune: Improving the Quality-Detectability Trade-off in Open-Weight LLM Watermarking2512.04044v1 · Yizhou Zhao, Zhiwei Steven Wu, Adam Block2025 · 0 citationsarXiv
All Roads Lead to Likelihood: The Value of Reinforcement Learning in Fine-Tuning2503.01067v2 · Gokul Swamy, Sanjiban Choudhury, Wen Sun et al.2025 · 0 citationsarXiv
Persona-Augmented Benchmarking: Evaluating LLMs Across Diverse Writing Styles2507.22168v2 · Kimberly Le Truong, Riccardo Fogliato, Hoda Heidari et al.2025 · 2 citationsarXiv
From Firewalls to Frontiers: AI Red-Teaming is a Domain-Specific Evolution of Cyber Red-Teaming2509.11398v1 · Anusha Sinha, Keltin Grimes, James Lucassen et al.2025 · 0 citationsarXiv
On the Benefits of Public Representations for Private Transfer Learning under Distribution Shift2312.15551v5 · Pratiksha Thaker, Amrith Setlur, Zhiwei Steven Wu et al.2023 · 0 citationsarXiv
Quantifying Privacy Risks of Public Statistics to Residents of Subsidized Housing2407.04776v2 · Ryan Steed, Diana Qing, Zhiwei Steven Wu2024 · 0 citationsHarvard Data Science Review Special Issue 6 (August 2025)
Measurement as Bricolage: Examining How Data Scientists Construct Target Variables for Predictive Modeling Tasks2507.02819v3 · Luke Guerdan, Devansh Saxena, Stevie Chancellor et al.2025 · 3 citationsarXiv
Kandinsky Conformal Prediction: Beyond Class- and Covariate-Conditional Coverage2502.17264v2 · Konstantina Bairaktari, Jiayun Wu, Zhiwei Steven Wu2025 · 0 citationsarXiv
Benchmarking Fraud Detectors on Private Graph Data2507.22347v1 · Alexander Goldberg, Giulia Fanti, Nihar Shah et al.2025 · 0 citationsarXiv
Choosing Public Datasets for Private Machine Learning via Gradient Subspace Distance2303.01256v2 · Xin Gu, Gautam Kamath, Zhiwei Steven Wu2023 · 3 citationsarXiv
Enhancing One-run Privacy Auditing with Quantile Regression-Based Membership Inference2506.15349v1 · Terrance Liu, Matteo Boglioni, Yiwei Fu et al.2025 · 0 citationsarXiv
Multi-group Uncertainty Quantification for Long-form Text Generation2407.21057v2 · Terrance Liu, Zhiwei Steven Wu2024 · 0 citationsarXiv
Generate-then-Verify: Reconstructing Data from Limited Published Statistics2504.21199v2 · Terrance Liu, Eileen Xiao, Adam Smith et al.2025 · 0 citationsarXiv
Persuasive Prediction via Decision Calibration2505.16141v1 · Jingwu Tang, Jiahao Zhang, Fei Fang et al.2025 · 0 citationsarXiv
Time-Uniform Self-Normalized Concentration for Vector-Valued Processes2310.09100v2 · Justin Whitehouse, Zhiwei Steven Wu, Aaditya Ramdas2023 · 0 citationsarXiv
Orthogonal Causal Calibration2406.01933v2 · Justin Whitehouse, Christopher Jung, Vasilis Syrgkanis et al.2024 · 0 citationsarXiv
Dimension-Free Decision Calibration for Nonlinear Loss Functions2504.15615v1 · Jingwu Tang, Jiayun Wu, Zhiwei Steven Wu et al.2025 · 0 citationsarXiv
Position: LLM Unlearning Benchmarks are Weak Measures of Progress2410.02879v2 · Pratiksha Thaker, Shengyuan Hu, Neil Kale et al.2024 · 6 citationsarXiv
Unlearning or Obfuscating? Jogging the Memory of Unlearned LLMs via Benign Relearning2406.13356v4 · Shengyuan Hu, Yiwei Fu, Zhiwei Steven Wu et al.2024 · 0 citationsarXiv
Inferentially-Private Private Information2410.17095v2 · Shuaiqi Wang, Shuran Zheng, Zinan Lin et al.2024 · 0 citationsarXiv
Ex-post Individually Rational Bayesian Persuasion2312.04973v2 · Jiahao Zhang, Shuran Zheng, Renato Paes Leme et al.2023 · 0 citationsarXiv
Competing Bandits: The Perils of Exploration Under Competition2007.10144v8 · Guy Aridor, Yishay Mansour, Aleksandrs Slivkins et al.2020 · 11 citationsarXiv
Regret Minimization in Stackelberg Games with Side Information2402.08576v4 · Keegan Harris, Zhiwei Steven Wu, Maria-Florina Balcan2024 · 1 citationarXiv
Adaptive Principal Component Regression with Applications to Panel Data2307.01357v3 · Anish Agarwal, Keegan Harris, Justin Whitehouse et al.2023 · 1 citationarXiv
Nonparametric extensions of randomized response for private confidence sets2202.08728v4 · Ian Waudby-Smith, Zhiwei Steven Wu, Aaditya Ramdas2022 · 1 citationarXiv
Multi-Agent Imitation Learning: Value is Easy, Regret is Hard2406.04219v2 · Jingwu Tang, Gokul Swamy, Fei Fang et al.2024 · 3 citationsarXiv
A Minimaximalist Approach to Reinforcement Learning from Human Feedback2401.04056v2 · Gokul Swamy, Christoph Dann, Rahul Kidambi et al.2024 · 3 citationsarXiv
Predictive Performance Comparison of Decision Policies Under Confounding2404.00848v2 · Luke Guerdan, Amanda Coston, Kenneth Holstein et al.2024 · 0 citationsarXiv
Hybrid Inverse Reinforcement Learning2402.08848v2 · Juntao Ren, Gokul Swamy, Zhiwei Steven Wu et al.2024 · 2 citationsarXiv
Bridging Multicalibration and Out-of-distribution Generalization Beyond Covariate Shift2406.00661v1 · Jiayun Wu, Jiashuo Liu, Peng Cui et al.2024 · 1 citationarXiv
Reconciling Model Multiplicity for Downstream Decision Making2405.19667v1 · Ally Yalei Du, Dung Daniel Ngo, Zhiwei Steven Wu2024 · 0 citationsarXiv
Reconstruction Attacks on Machine Unlearning: Simple Models are Vulnerable2405.20272v1 · Martin Bertran, Shuai Tang, Michael Kearns et al.2024 · 11 citationsarXiv
Differentially Private SGD Without Clipping Bias: An Error-Feedback Approach2311.14632v2 · Xinwei Zhang, Zhiqi Bu, Zhiwei Steven Wu et al.2023 · 0 citationsarXiv
Differentially Private Bayesian Persuasion2402.15872v1 · Yuqi Pan, Zhiwei Steven Wu, Haifeng Xu et al.2024 · 0 citationsarXiv
The Virtues of Pessimism in Inverse Reinforcement Learning2402.02616v2 · David Wu, Gokul Swamy, J. Andrew Bagnell et al.2024 · 0 citationsarXiv
Inverse Reinforcement Learning without Reinforcement Learning2303.14623v4 · Gokul Swamy, Sanjiban Choudhury, J. Andrew Bagnell et al.2023 · 1 citationarXiv
Strategyproof Decision-Making in Panel Data Settings and Beyond2211.14236v4 · Keegan Harris, Anish Agarwal, Chara Podimata et al.2022 · 1 citationarXiv
Membership Inference Attacks on Diffusion Models via Quantile Regression2312.05140v1 · Shuai Tang, Zhiwei Steven Wu, Sergul Aydore et al.2023 · 2 citationsarXiv
Adaptive Privacy Composition for Accuracy-first Mechanisms2306.13824v2 · Ryan Rogers, Gennady Samorodnitsky, Zhiwei Steven Wu et al.2023 · 1 citationarXiv
Strategic Apple Tasting2306.06250v2 · Keegan Harris, Chara Podimata, Zhiwei Steven Wu2023 · 1 citationarXiv
Career total: 252 works. 144 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.