Research Interests

I am broadly interested in problems at the frontier of machine learning, learning theory, and computational social science. Here are some recent topics I am interested in:

Manuscripts & Preprints

(* for equal contribution; (α-β) for alphabetical ordering; papers with purple titles are not on arXiv yet)

Making Predictors More Reliable with Selective Recalibration Submitted

Tom Zollo, Zhun DengJake Snell, Toniann Pitassi, Richard Zemel

Taking a Break: The Optimal Stopping Problem for User Engagement Draft in progress

Zhun Deng, He Sun, Guannan Qu, David Parkes


(* for equal contribution; (α-β) for alphabetical ordering)

Conference Proceedings


Learning and Forgetting Unsafe Examples in Large Language Models ICML 2024

Jiachen Zhao, Zhun Deng,  David Madras, James Zou, Mengye Ren

Prompt Risk Control: A Rigorous Framework for Responsible Deployment of Large Language Models ICLR 2024

Tom Zello, Todd Morrill*, Zhun Deng*,  Jake Snell, Toniann Pitassi, Richard Zemel


Distribution-free Statistical Dispersion Control for Societal Applications  NeurIPS (spotlight, top 3% among submissions) 2023

Zhun Deng, Tom Zello, Jake Snell, Toniann Pitassi, Richard Zemel

PICProp: Physics-Informed Confidence Propagation for Uncertainty Quantification  NeurIPS 2023

Qianli Shen, Wai Hoh Tang, Zhun Deng, Apostolos Psaros, Kenji Kawaguchi

Decision-Aware Conditional GANs for Time Series Data  ICAIF  (oral presentation) 2023

He Sun, Zhun Deng, Hui Chen, David Parkes

How Does Information Bottleneck Help Deep Learning  ICML 2023

Kenji Kawaguchi*, Zhun Deng*, Xu Ji*, Jiaoyang Huang

Reinforcement Learning with Stepwise Fairness Constraints  AISTATS 2023 

Zhun Deng, He Sun, Zhiwei Steven Wu, Linjun Zhang, David Parkes

Understanding Multimodal Contrastive Learning and Incoportate Paired Data AISTATS 2023 

Ryumei Nakada, Ibriham Golluk, Zhun Deng, Wenlong Ji, James Zou,  Linjun Zhang

FIFA: Making Fairness More Generalizable in Classifiers Trained on Imbalanced Data  ICLR 2023

Zhun Deng, Jiayao Zhang, Linjun Zhang, Ting Ye, Yates Coley, Weijie Su, James Zou

Quantile Risk Control: a Flexible Framework for Bounding the Probability of High-loss Predictions  ICLR 2023

Jake Snell, Tom Zello, Zhun Deng, Toniann Pitassi, Richard Zemel

Happymap: A Generalized Multi-calibration Method  ITCS 2023

(α-β) Zhun Deng, Cynthia Dwork, Linjun Zhang


When and How Mixup Improves Calibration  ICML 2022

Linjun Zhang*, Zhun Deng*, Kenji Kawaguchi, James Zou

Robustness Implies Generalization via Data-dependent Generalization Bounds ICML (long presentation, top 2% among submissions) 2022 

Kenji Kawaguchi, Zhun Deng, Kyle Luh, Jiaoyang Huang

An Unconstrained Layer-Peeled Perspective on Neural Collapse  ICLR 2022

Wenlong Ji, Yiping Lu, Yiliang Zhang, Zhun Deng, Weijie Su


Adversarial Training Helps Transfer Learning via Better Representations  NeurIPS 2021

Zhun Deng*, Linjun Zhang*, Kailas Vodrahalli, Kenji Kawaguchi, James Zou

Toward Better Generalization Bounds with Locally Elastic Stability  ICML 2021

Zhun Deng, Hangfeng He, Weijie Su

Improving Adversarial Robustness via Unlabeled Out-of-Domain Data  AISTATS (oral presentation, top 3% among submissions) 2021

Zhun Deng*, Linjun Zhang*, Amirata Ghorbani, James Zou

How Does Mixup Help With Robustness and Generalization?  ICLR (spotlight, top 5% among submissions) 2021

Linjun Zhang*, Zhun Deng*, Kenji Kawaguchi*, Amirata Ghorbani, James Zou

The Role of Gradient Noise in the Optimization of Neural Networks  IEEE Big Data 2021

(α-β) Zhun Deng, Jiaoyang Huang, Kenji Kawaguchi


Interpreting Robust Optimization via Adversarial Influence Functions  ICML 2020

(α-β) Zhun Deng, Cynthia Dwork, Jialiang Wang, Linjun Zhang

Towards Understanding the Dynamics of the First-Order Adversaries  ICML 2020

Zhun Deng, Hangfeng He, Jiaoyang Huang, Weijie Su


The Number of Independent Sets in Hexagonal Graphs ISIT 2018

Zhun Deng, Jie Ding, Kathryn Heal, Vahid Tarokh

Workshop Proceedings


Last-layer Fairness Fine-tuning is Simple and Effective for Neural Networks  ICML Workshop 2023

Yuzhen Mao,  Zhun Deng, Huaxiu Yao, Ting Ye, Kenji Kawaguchi, James Zou


Differential Privacy After the Fact: The Case of Congressional Reapportionment  TPDP 2019

(α-β) Zhun Deng, Cynthia Dwork, Adam Smith

Journal Publications


The Power of Contrast for Feature Learning: A Theoretical Analysis  The Journal of Machine Learning Research (JMLR), 24(330):1-78, 2023.

Wenlong Ji, Zhun Deng, Ryumei Nakada, James Zou, Linjun Zhang


Understanding Dynamics of Learning Nonlinear Representations and its Application  Neural Computation, 34(4), 991-1018, MIT Press, 2022.

Kenji Kawaguchi, Linjun Zhang, Zhun Deng