Weijie J. Su

Chendi Wang

CoRR, 2024

A Statistical Viewpoint on Differential Privacy: Hypothesis Testing, Representation and Blackwell's Theorem.

[BibT_eX]

[DOI]

CoRR, 2024

A Law of Next-Token Prediction in Large Language Models.

[BibT_eX]

[DOI]

CoRR, 2024

Analysis of the ICML 2023 Ranking Data: Can Authors' Opinions of Their Own Papers Assist Peer Review in Machine Learning?

[BibT_eX]

[DOI]

CoRR, 2024

Fine-Tuning Linear Layers Only Is a Simple yet Effective Way for Task Arithmetic.

[BibT_eX]

[DOI]

CoRR, 2024

Tackling GenAI Copyright Issues: Originality Estimation and Genericization.

[BibT_eX]

[DOI]

Hiroaki Chiba-Okabe

CoRR, 2024

Multi-Modal and Multi-Agent Systems Meet Rationality: A Survey.

[BibT_eX]

[DOI]

CoRR, 2024

AI Risk Management Should Incorporate Both Safety and Security.

[BibT_eX]

[DOI]

CoRR, 2024

On the Algorithmic Bias of Aligning Large Language Models with RLHF: Preference Collapse and Matching Regularization.

[BibT_eX]

[DOI]

CoRR, 2024

An Economic Solution to Copyright Challenges of Generative AI.

[BibT_eX]

[DOI]

CoRR, 2024

A Statistical Framework of Watermarks for Large Language Models: Pivot, Detection Efficiency and Optimal Rules.

[BibT_eX]

[DOI]

CoRR, 2024

Provable Multi-Party Reinforcement Learning with Diverse Human Feedback.

[BibT_eX]

[DOI]

CoRR, 2024

WildfireGPT: Tailored Large Language Model for Wildfire Analysis.

[BibT_eX]

[DOI]

Yangxinyu Xie

Tanwi Mallick

Joshua David Bergerson

CoRR, 2024

Can AI Be as Creative as Humans?

[BibT_eX]

[DOI]

CoRR, 2024

Neural Collapse meets Differential Privacy: Curious behaviors of NoisyGD with Near-Perfect Representation Learning.

[BibT_eX]

[DOI]

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Shifted Interpolation for Differential Privacy.

[BibT_eX]

[DOI]

Jinho Bok

Jason M. Altschuler

Proceedings of the Forty-first International Conference on Machine Learning, 2024

A Peek into Token Bias: Large Language Models Are Not Yet Genuine Reasoners.

[BibT_eX]

[DOI]

Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024

Bridging the Gap: Rademacher Complexity in Robust and Standard Generalization.

[BibT_eX]

[DOI]

Proceedings of the Thirty Seventh Annual Conference on Learning Theory, June 30, 2024

2023

On Quantum Speedups for Nonconvex Optimization via Quantum Tunneling Walks.

[BibT_eX]

[DOI]

Yizhou Liu

Tongyang Li

Quantum, June, 2023

HiGrad: Uncertainty Quantification for Online Learning and Stochastic Approximation.

[BibT_eX]

[DOI]

Yuancheng Zhu

J. Mach. Learn. Res., 2023

On Learning Rates and Schrödinger Operators.

[BibT_eX]

[DOI]

Bin Shi

Michael I. Jordan

J. Mach. Learn. Res., 2023

Minimax Estimation for Personalized Federated Learning: An Alternative between FedAvg and Local Training?

[BibT_eX]

[DOI]

J. Mach. Learn. Res., 2023

What Should Data Science Education Do with Large Language Models?

[BibT_eX]

[DOI]

CoRR, 2023

DP-HyPO: An Adaptive Private Hyperparameter Optimization Framework.

[BibT_eX]

[DOI]

CoRR, 2023

Reward Collapse in Aligning Large Language Models.

[BibT_eX]

[DOI]

CoRR, 2023

The Isotonic Mechanism for Exponential Family Estimation.

[BibT_eX]

[DOI]

Yuling Yan

Jianqing Fan

CoRR, 2023

Challenges towards the Next Frontier in Privacy.

[BibT_eX]

[DOI]

CoRR, 2023

Unified Enhancement of Privacy Bounds for Mixture Mechanisms via f-Differential Privacy.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

DP-HyPO: An Adaptive Private Framework for Hyperparameter Optimization.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

The Implicit Regularization of Dynamical Stability in Stochastic Gradient Descent.

[BibT_eX]

[DOI]

Lei Wu

Proceedings of the International Conference on Machine Learning, 2023

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

[BibT_eX]

[DOI]

Proceedings of the Eleventh International Conference on Learning Representations, 2023

2022

The Price of Competition: Effect Size Heterogeneity Matters in High Dimensions.

[BibT_eX]

[DOI]

Hua Wang

Yachong Yang

IEEE Trans. Inf. Theory, 2022

Understanding the acceleration phenomenon via high-resolution differential equations.

[BibT_eX]

[DOI]

Math. Program., 2022

A Law of Data Separation in Deep Learning.

[BibT_eX]

[DOI]

CoRR, 2022

A Truthful Owner-Assisted Scoring Mechanism.

[BibT_eX]

[DOI]

CoRR, 2022

Analytical Composition of Differential Privacy via the Edgeworth Accountant.

[BibT_eX]

[DOI]

CoRR, 2022

Causal Inference Principles for Reasoning about Commonsense Causality.

[BibT_eX]

[DOI]

CoRR, 2022

ROCK: Causal Inference Principles for Reasoning about Commonsense Causality.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2022

An Unconstrained Layer-Peeled Perspective on Neural Collapse.

[BibT_eX]

[DOI]

Proceedings of the Tenth International Conference on Learning Representations, 2022

Weighted Training for Cross-Task Learning.

[BibT_eX]

[DOI]

Proceedings of the Tenth International Conference on Learning Representations, 2022

2021

Algorithmic Analysis and Statistical Estimation of SLOPE via Approximate Message Passing.

[BibT_eX]

[DOI]

IEEE Trans. Inf. Theory, 2021

Differentially private false discovery rate control.

[BibT_eX]

[DOI]

Cynthia Dwork

Li Zhang

J. Priv. Confidentiality, 2021

Neurashed: A Phenomenological Model for Imitating Deep Learning Training.

[BibT_eX]

[DOI]

CoRR, 2021

On the Convergence of Deep Learning with Differential Privacy.

[BibT_eX]

[DOI]

CoRR, 2021

Characterizing the SLOPE Trade-off: A Variational Perspective and the Donoho-Tanner Limit.

[BibT_eX]

[DOI]

CoRR, 2021

Rejoinder: Gaussian Differential Privacy.

[BibT_eX]

[DOI]

Jinshuo Dong

Aaron Roth

CoRR, 2021

A Theorem of the Alternative for Personalized Federated Learning.

[BibT_eX]

[DOI]

CoRR, 2021

Layer-Peeled Model: Toward Understanding Well-Trained Deep Neural Networks.

[BibT_eX]

[DOI]

CoRR, 2021

Imitating Deep Learning Dynamics via Locally Elastic Stochastic Differential Equations.

[BibT_eX]

[DOI]

Jiayao Zhang

Hua Wang

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

You Are the Best Reviewer of Your Own Papers: An Owner-Assisted Scoring Mechanism.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

A Central Limit Theorem for Differentially Private Query Answering.

[BibT_eX]

[DOI]

Jinshuo Dong

Linjun Zhang

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Oneshot Differentially Private Top-k Selection.

[BibT_eX]

[DOI]

Gang Qiao

Li Zhang

Proceedings of the 38th International Conference on Machine Learning, 2021

Toward Better Generalization Bounds with Locally Elastic Stability.

[BibT_eX]

[DOI]

Zhun Deng

Proceedings of the 38th International Conference on Machine Learning, 2021

Federated f-Differential Privacy.

[BibT_eX]

[DOI]

Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021

2020

Sharp Bias-variance Tradeoffs of Hard Parameter Sharing in High-dimensional Linear Regression.

[BibT_eX]

[DOI]

CoRR, 2020

Benign Overfitting and Noisy Features.

[BibT_eX]

[DOI]

Zhu Li

Dino Sejdinovic

CoRR, 2020

The Complete Lasso Tradeoff Diagram.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Label-Aware Neural Tangent Kernel: Toward Better Generalization and Local Elasticity.

[BibT_eX]

[DOI]

Shuxiao Chen

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Sharp Composition Bounds for Gaussian Differential Privacy via Edgeworth Expansion.

[BibT_eX]

[DOI]

Proceedings of the 37th International Conference on Machine Learning, 2020

Towards Understanding the Dynamics of the First-Order Adversaries.

[BibT_eX]

[DOI]

Proceedings of the 37th International Conference on Machine Learning, 2020

The Local Elasticity of Neural Networks.

[BibT_eX]

[DOI]

Proceedings of the 8th International Conference on Learning Representations, 2020

2019

Deep Learning with Gaussian Differential Privacy.

[BibT_eX]

[DOI]

CoRR, 2019

Quantifying Intrinsic Uncertainty in Classification via Deep Dirichlet Mixture Networks.

[BibT_eX]

[DOI]

CoRR, 2019

Gaussian Differential Privacy.

[BibT_eX]

[DOI]

Jinshuo Dong

Aaron Roth

CoRR, 2019

Acceleration via Symplectic Discretization of High-Resolution Differential Equations.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

2016

A Differential Equation for Modeling Nesterov's Accelerated Gradient Method: Theory and Insights.

[BibT_eX]

[DOI]

Stephen P. Boyd

Emmanuel J. Candès

J. Mach. Learn. Res., 2016

2015

False Discoveries Occur Early on the Lasso Path.

[BibT_eX]

[DOI]

Malgorzata Bogdan

Emmanuel J. Candès

CoRR, 2015

Private False Discovery Rate Control.

[BibT_eX]

[DOI]

Cynthia Dwork

Li Zhang

CoRR, 2015

SLOPE is Adaptive to Unknown Sparsity and Asymptotically Minimax.

[BibT_eX]

[DOI]

Emmanuel J. Candès