Hongyang R. Zhang

发表

Improved Regularization and Robustness for Fine-tuning in Neural Networks pdf

Dongyue Li, Hongyang R. Zhang, Dongyue Li, 2021, NeurIPS.

Algorithmic Regularization in Over-parameterized Matrix Sensing and Neural Networks with Quadratic Activations

Hongyang Zhang, Yuanzhi Li, Tengyu Ma, 2017, COLT.

Algorithmic Regularization in Over-parameterized Matrix Recovery pdf

Yuanzhi Li, Tengyu Ma, Hongyang Zhang, 2017, ArXiv.

Theoretically Principled Trade-off between Robustness and Accuracy

Michael I. Jordan, Eric P. Xing, Laurent El Ghaoui, 2019, ICML.

Incentive Ratios of Fisher Markets

Ning Chen, Xiaotie Deng, Hongyang Zhang, 2012, ICALP.

Self-Adaptive Training: beyond Empirical Risk Minimization

Hongyang R. Zhang, Lang Huang, Chaoning Zhang, 2020, NeurIPS.

Deep Neural Networks with Multi-Branch Architectures Are Intrinsically Less Non-Convex

Ruslan Salakhutdinov, Hongyang Zhang, Junru Shao, 2019, AISTATS.

Optimal Analysis of Subset-Selection Based L_p Low Rank Approximation

Pradeep Ravikumar, Chen Dan, Hong Wang, 2019, 1910.13618.

On the Generalization Effects of Linear Transformations in Data Augmentation

Sen Wu, Christopher Ré, Gregory Valiant, 2020, ICML.

Appendix A – Proofs

Hongyang R. Zhang, Zhouchen Lin, Hongyang Zhang, 2017 .

Towards Transferable Adversarial Perturbations with Minimum Norm

Hongyang R. Zhang, Chaoning Zhang, Fangcheng Liu, 2021 .

Noise-Tolerant Interactive Learning from Pairwise Comparisons

Hongyang R. Zhang, Aarti Singh, A. Dubrawski, 2017, 1704.05820.

X Primal Problem ( 1 ) Bi-Dual Problem ( 2 ) Strong Duality By Theorem 3 . 3 + Dual Certificate Surface of ( 1 ) Surface of ( 2 ) Common Optimal Solution AB

David P. Woodruff, Hongyang R. Zhang, Yingyu Liang, 2017 .

Improved Worst-Group Robustness via Classifier Retraining on Independent Splits

Huy L. Nguyen, Thien Hai Nguyen, Hongyang R. Zhang, 2022, ArXiv.

Learning Over-Parametrized Two-Layer Neural Networks beyond NTK

Tengyu Ma, Yuanzhi Li, Hongyang R. Zhang, 2020, COLT.

Regression Phalanxes

Hongyang R. Zhang, W. Welch, R. Zamar, 2017, 1707.00727.

Causal Balancing for Domain Generalization

William Yang Wang, Michael Stephen Saxon, Hongyang R. Zhang, 2022, ArXiv.

RetrievalGuard: Provably Robust 1-Nearest Neighbor Image Retrieval

Hongyang R. Zhang, Yihan Wu, Heng Huang, 2022, ICML.

New Advances in Sparse Learning, Deep Networks, and Adversarial Learning: Theory and Applications

Hongyang R. Zhang, Hongyang Zhang, 2019 .

Causal Balancing for Domain Generalization

William Yang Wang, Michael Stephen Saxon, Hongyang R. Zhang, 2022, ArXiv.

Recovery from Non-Decomposable Distance Oracles

David P. Woodruff, Hongyang R. Zhang, Zhuangfei Hu, 2022, ArXiv.

Causal Balancing for Domain Generalization

William Yang Wang, Michael Stephen Saxon, Hongyang R. Zhang, 2022, ArXiv.

Robust Fine-Tuning of Deep Neural Networks with Hessian-based Generalization Guarantees

Hongyang R. Zhang, Dongyue Li, Haotian Ju, 2022, International Conference on Machine Learning.

Improved Group Robustness via Classifier Retraining on Independent Splits

Huy L. Nguyen, Thien Hai Nguyen, Hongyang R. Zhang, 2022, 2204.09583.

Self-Adaptive Training: Bridging the Supervised and Self-Supervised Learning

Hongyang R. Zhang, Lang Huang, Chaoning Zhang, 2021, IEEE transactions on pattern analysis and machine intelligence.

Building Robust Ensembles via Margin Boosting

Aaron C. Courville, Arun Sai Suggala, Yoshua Bengio, 2022, ICML.

Robust Fine-Tuning of Deep Neural Networks with Hessian-based Generalization Guarantees

Hongyang R. Zhang, Dongyue Li, Haotian Ju, 2022, International Conference on Machine Learning.

Understanding the Impact of Adversarial Robustness on Accuracy Disparity

Hongyang R. Zhang, Yuzheng Hu, Fan Wu, 2022, ArXiv.

Direct-Effect Risk Minimization for Domain Generalization

Hongyang R. Zhang, Yuhui Li, Zejia Wu, 2022, ArXiv.

Least angle regression for model selection

Ruben H. Zamar, Hongyang Zhang, Hongyang R. Zhang, 2014 .

Towards Transferable Unrestricted Adversarial Examples with Minimum Changes

Hongyang R. Zhang, Chaoning Zhang, Fangcheng Liu, 2022, 2023 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML).