Weijie J. Su

Publication Activity (10 Years)

Years Active: 2018-2024
Publications (10 Years): 79

Top Topics

Differentially Private

Differential Privacy

Top Venues

Publications

Haonan Wang, James Zou, Michael Mozer, Anirudh Goyal, Alex Lamb, Linjun Zhang, Weijie J. Su, Zhun Deng, Michael Qizhe Xie, Hannah Brown, Kenji Kawaguchi
Can AI Be as Creative as Humans? CoRR (2024)
Jiancong Xiao, Ziniu Li, Xingyu Xie, Emily J. Getzen, Cong Fang, Qi Long, Weijie J. Su
On the Algorithmic Bias of Aligning Large Language Models with RLHF: Preference Collapse and Matching Regularization. CoRR (2024)
Xiangyu Qi, Yangsibo Huang, Yi Zeng, Edoardo Debenedetti, Jonas Geiping, Luxi He, Kaixuan Huang, Udari Madhushani, Vikash Sehwag, Weijia Shi, Boyi Wei, Tinghao Xie, Danqi Chen, Pin-Yu Chen, Jeffrey Ding, Ruoxi Jia, Jiaqi Ma, Arvind Narayanan, Weijie J. Su, Mengdi Wang, Chaowei Xiao, Bo Li, Dawn Song, Peter Henderson, Prateek Mittal
AI Risk Management Should Incorporate Both Safety and Security. CoRR (2024)
Chendi Wang, Yuqing Zhu, Weijie J. Su, Yu-Xiang Wang
Neural Collapse Meets Differential Privacy: Curious Behaviors of NoisyGD with Near-perfect Representation Learning. CoRR (2024)
Xiang Li, Feng Ruan, Huiyuan Wang, Qi Long, Weijie J. Su
A Statistical Framework of Watermarks for Large Language Models: Pivot, Detection Efficiency and Optimal Rules. CoRR (2024)
Jiancong Xiao, Ruoyu Sun, Qi Long, Weijie J. Su
Bridging the Gap: Rademacher Complexity in Robust and Standard Generalization. CoRR (2024)
Huiying Zhong, Zhun Deng, Weijie J. Su, Zhiwei Steven Wu, Linjun Zhang
Provable Multi-Party Reinforcement Learning with Diverse Human Feedback. CoRR (2024)
Bowen Jiang, Yangxinyu Xie, Xiaomeng Wang, Weijie J. Su, Camillo J. Taylor, Tanwi Mallick
Multi-Modal and Multi-Agent Systems Meet Rationality: A Survey. CoRR (2024)
Matteo Sordello, Niccolò Dalmasso, Hangfeng He, Weijie J. Su
Robust Learning Rate Selection for Stochastic Optimization via Splitting Diagnostic. Trans. Mach. Learn. Res. 2024 (2024)
Ruochen Jin, Bojian Hou, Jiancong Xiao, Weijie J. Su, Li Shen
Fine-Tuning Linear Layers Only Is a Simple yet Effective Way for Task Arithmetic. CoRR (2024)
Bowen Jiang, Yangxinyu Xie, Zhuoqun Hao, Xiaomeng Wang, Tanwi Mallick, Weijie J. Su, Camillo J. Taylor, Dan Roth
A Peek into Token Bias: Large Language Models Are Not Yet Genuine Reasoners. CoRR (2024)
Jiachen T. Wang, Zhun Deng, Hiroaki Chiba-Okabe, Boaz Barak, Weijie J. Su
An Economic Solution to Copyright Challenges of Generative AI. CoRR (2024)
Hiroaki Chiba-Okabe, Weijie J. Su
Tackling GenAI Copyright Issues: Originality Estimation and Genericization. CoRR (2024)
Hua Wang, Sheng Gao, Huanyu Zhang, Weijie J. Su, Milan Shen
DP-HyPO: An Adaptive Private Hyperparameter Optimization Framework. CoRR (2023)
Lei Wu, Weijie J. Su
The Implicit Regularization of Dynamical Stability in Stochastic Gradient Descent. CoRR (2023)
Hua Wang, Sheng Gao, Huanyu Zhang, Weijie J. Su, Milan Shen
DP-HyPO: An Adaptive Private Framework for Hyperparameter Optimization. NeurIPS (2023)
Weijie J. Su, Yuancheng Zhu
HiGrad: Uncertainty Quantification for Online Learning and Stochastic Approximation. J. Mach. Learn. Res. 24 (2023)
Chendi Wang, Buxin Su, Jiayuan Ye, Reza Shokri, Weijie J. Su
Unified Enhancement of Privacy Bounds for Mixture Mechanisms via f-Differential Privacy. NeurIPS (2023)
Ziang Song, Tianle Cai, Jason D. Lee, Weijie J. Su
Reward Collapse in Aligning Large Language Models. CoRR (2023)
Xinming Tu, James Zou, Weijie J. Su, Linjun Zhang
What Should Data Science Education Do with Large Language Models? CoRR (2023)
Chendi Wang, Buxin Su, Jiayuan Ye, Reza Shokri, Weijie J. Su
Unified Enhancement of Privacy Bounds for Mixture Mechanisms via f-Differential Privacy. CoRR (2023)
Yuling Yan, Weijie J. Su, Jianqing Fan
The Isotonic Mechanism for Exponential Family Estimation. CoRR (2023)
Zhun Deng, Jiayao Zhang, Linjun Zhang, Ting Ye, Yates Coley, Weijie J. Su, James Zou
FIFA: Making Fairness More Generalizable in Classifiers Trained on Imbalanced Data. ICLR (2023)
Lei Wu, Weijie J. Su
The Implicit Regularization of Dynamical Stability in Stochastic Gradient Descent. ICML (2023)
Rachel Cummings, Damien Desfontaines, David Evans, Roxana Geambasu, Matthew Jagielski, Yangsibo Huang, Peter Kairouz, Gautam Kamath, Sewoong Oh, Olga Ohrimenko, Nicolas Papernot, Ryan Rogers, Milan Shen, Shuang Song, Weijie J. Su, Andreas Terzis, Abhradeep Thakurta, Sergei Vassilvitskii, Yu-Xiang Wang, Li Xiong, Sergey Yekhanin, Da Yu, Huanyu Zhang, Wanrong Zhang
Challenges towards the Next Frontier in Privacy. CoRR (2023)
Yizhou Liu, Weijie J. Su, Tongyang Li
On Quantum Speedups for Nonconvex Optimization via Quantum Tunneling Walks. Quantum 7 (2023)
Jiayao Zhang, Hongming Zhang, Dan Roth, Weijie J. Su
Causal Inference Principles for Reasoning about Commonsense Causality. CoRR (2022)
Zhun Deng, Jiayao Zhang, Linjun Zhang, Ting Ye, Yates Coley, Weijie J. Su, James Zou
FIFA: Making Fairness More Generalizable in Classifiers Trained on Imbalanced Data. CoRR (2022)
Hua Wang, Yachong Yang, Weijie J. Su
The Price of Competition: Effect Size Heterogeneity Matters in High Dimensions. IEEE Trans. Inf. Theory 68 (8) (2022)
Hua Wang, Sheng Gao, Huanyu Zhang, Milan Shen, Weijie J. Su
Analytical Composition of Differential Privacy via the Edgeworth Accountant. CoRR (2022)
Bin Shi, Simon S. Du, Michael I. Jordan, Weijie J. Su
Understanding the acceleration phenomenon via high-resolution differential equations. Math. Program. 195 (1) (2022)
Wenlong Ji, Yiping Lu, Yiliang Zhang, Zhun Deng, Weijie J. Su
An Unconstrained Layer-Peeled Perspective on Neural Collapse. ICLR (2022)
Jiayao Zhang, Hongming Zhang, Weijie J. Su, Dan Roth
ROCK: Causal Inference Principles for Reasoning about Commonsense Causality. ICML (2022)
Shuxiao Chen, Koby Crammer, Hangfeng He, Dan Roth, Weijie J. Su
Weighted Training for Cross-Task Learning. ICLR (2022)
Weijie J. Su
A Truthful Owner-Assisted Scoring Mechanism. CoRR (2022)
Hangfeng He, Weijie J. Su
A Law of Data Separation in Deep Learning. CoRR (2022)
Yizhou Liu, Weijie J. Su, Tongyang Li
On Quantum Speedups for Nonconvex Optimization via Quantum Tunneling Walks. CoRR (2022)
Shuxiao Chen, Qinqing Zheng, Qi Long, Weijie J. Su
A Theorem of the Alternative for Personalized Federated Learning. CoRR (2021)
Jiayao Zhang, Hua Wang, Weijie J. Su
Imitating Deep Learning Dynamics via Locally Elastic Stochastic Differential Equations. CoRR (2021)
Cong Fang, Hangfeng He, Qi Long, Weijie J. Su
Layer-Peeled Model: Toward Understanding Well-Trained Deep Neural Networks. CoRR (2021)
Zhiqi Bu, Hua Wang, Qi Long, Weijie J. Su
On the Convergence of Deep Learning with Differential Privacy. CoRR (2021)
Shuxiao Chen, Koby Crammer, Hangfeng He, Dan Roth, Weijie J. Su
Weighted Training for Cross-Task Learning. CoRR (2021)
Jinshuo Dong, Aaron Roth, Weijie J. Su
Rejoinder: Gaussian Differential Privacy. CoRR (2021)
Cynthia Dwork, Weijie J. Su, Li Zhang
Differentially private false discovery rate control. J. Priv. Confidentiality 11 (2) (2021)
Weijie J. Su
You Are the Best Reviewer of Your Own Papers: An Owner-Assisted Scoring Mechanism. CoRR (2021)
Zhiqi Bu, Jason M. Klusowski, Cynthia Rush, Weijie J. Su
Algorithmic Analysis and Statistical Estimation of SLOPE via Approximate Message Passing. IEEE Trans. Inf. Theory 67 (1) (2021)
Wenlong Ji, Yiping Lu, Yiliang Zhang, Zhun Deng, Weijie J. Su
An Unconstrained Layer-Peeled Perspective on Neural Collapse. CoRR (2021)
Qinqing Zheng, Shuxiao Chen, Qi Long, Weijie J. Su
Federated f-Differential Privacy. AISTATS (2021)
Gang Qiao, Weijie J. Su, Li Zhang
Oneshot Differentially Private Top-k Selection. ICML (2021)
Jiayao Zhang, Hua Wang, Weijie J. Su
Imitating Deep Learning Dynamics via Locally Elastic Stochastic Differential Equations. NeurIPS (2021)
Weijie J. Su
You Are the Best Reviewer of Your Own Papers: An Owner-Assisted Scoring Mechanism. NeurIPS (2021)
Weijie J. Su
Neurashed: A Phenomenological Model for Imitating Deep Learning Training. CoRR (2021)
Zhiqi Bu, Jason M. Klusowski, Cynthia Rush, Weijie J. Su
Characterizing the SLOPE Trade-off: A Variational Perspective and the Donoho-Tanner Limit. CoRR (2021)
Gang Qiao, Weijie J. Su, Li Zhang
Oneshot Differentially Private Top-k Selection. CoRR (2021)
Jinshuo Dong, Weijie J. Su, Linjun Zhang
A Central Limit Theorem for Differentially Private Query Answering. CoRR (2021)
Zhun Deng, Hangfeng He, Weijie J. Su
Toward Better Generalization Bounds with Locally Elastic Stability. ICML (2021)
Jinshuo Dong, Weijie J. Su, Linjun Zhang
A Central Limit Theorem for Differentially Private Query Answering. NeurIPS (2021)
Qinqing Zheng, Shuxiao Chen, Qi Long, Weijie J. Su
Federated $f$-Differential Privacy. CoRR (2021)
Qinqing Zheng, Jinshuo Dong, Qi Long, Weijie J. Su
Sharp Composition Bounds for Gaussian Differential Privacy via Edgeworth Expansion. ICML (2020)
Zhun Deng, Hangfeng He, Jiaoyang Huang, Weijie J. Su
Towards Understanding the Dynamics of the First-Order Adversaries. ICML (2020)
Bin Shi, Weijie J. Su, Michael I. Jordan
On Learning Rates and Schrödinger Operators. CoRR (2020)
Zhun Deng, Hangfeng He, Jiaoyang Huang, Weijie J. Su
Towards Understanding the Dynamics of the First-Order Adversaries. CoRR (2020)
Shuxiao Chen, Hangfeng He, Weijie J. Su
Label-Aware Neural Tangent Kernel: Toward Better Generalization and Local Elasticity. NeurIPS (2020)
Zhun Deng, Hangfeng He, Weijie J. Su
Toward Better Generalization Bounds with Locally Elastic Stability. CoRR (2020)
Shuxiao Chen, Hangfeng He, Weijie J. Su
Label-Aware Neural Tangent Kernel: Toward Better Generalization and Local Elasticity. CoRR (2020)
Hua Wang, Yachong Yang, Weijie J. Su
The Price of Competition: Effect Size Heterogeneity Matters in High Dimensions. CoRR (2020)
Qinqing Zheng, Jinshuo Dong, Qi Long, Weijie J. Su
Sharp Composition Bounds for Gaussian Differential Privacy via Edgeworth Expansion. CoRR (2020)
Hua Wang, Yachong Yang, Zhiqi Bu, Weijie J. Su
The Complete Lasso Tradeoff Diagram. CoRR (2020)
Hongyang R. Zhang, Fan Yang, Sen Wu, Weijie J. Su, Christopher Ré
Sharp Bias-variance Tradeoffs of Hard Parameter Sharing in High-dimensional Linear Regression. CoRR (2020)
Hangfeng He, Weijie J. Su
The Local Elasticity of Neural Networks. ICLR (2020)
Hua Wang, Yachong Yang, Zhiqi Bu, Weijie J. Su
The Complete Lasso Tradeoff Diagram. NeurIPS (2020)
Zhiqi Bu, Jason M. Klusowski, Cynthia Rush, Weijie J. Su
Algorithmic Analysis and Statistical Estimation of SLOPE via Approximate Message Passing. CoRR (2019)
Bin Shi, Simon S. Du, Weijie J. Su, Michael I. Jordan
Acceleration via Symplectic Discretization of High-Resolution Differential Equations. CoRR (2019)
Zhiqi Bu, Jason M. Klusowski, Cynthia Rush, Weijie J. Su
Algorithmic Analysis and Statistical Estimation of SLOPE via Approximate Message Passing. NeurIPS (2019)
Jinshuo Dong, Aaron Roth, Weijie J. Su
Gaussian Differential Privacy. CoRR (2019)
Hangfeng He, Weijie J. Su
The Local Elasticity of Neural Networks. CoRR (2019)
Bin Shi, Simon S. Du, Weijie J. Su, Michael I. Jordan
Acceleration via Symplectic Discretization of High-Resolution Differential Equations. NeurIPS (2019)
Zhiqi Bu, Jinshuo Dong, Qi Long, Weijie J. Su
Deep Learning with Gaussian Differential Privacy. CoRR (2019)
Bin Shi, Simon S. Du, Michael I. Jordan, Weijie J. Su
Understanding the Acceleration Phenomenon via High-Resolution Differential Equations. CoRR (2018)