Jiaoyang Huang

Assistant Professor of Statistics and Data Science

Contact Information

Primary Email:
huangjy@wharton.upenn.edu
Office Phone:
215-573-0536

office Address:
309 Academic Research Building
265 South 37th Street
Philadelphia, PA 19104

Research Interests: Random matrix theory, random graphs, interacting particle systems, optimization of deep neural networks, posterior sampling, and uncertainty quantification of large scale inverse problems.

Links: Personal Website, Google Scholar

Research

Kenji Kawaguchi, Zhun Deng, Xu Ji, Jiaoyang Huang (2023), How Does Information Bottleneck Help Deep Learning?, Proceedings of the 40th International Conference on Machine Learning (ICML), 202 ().
Jiaoyang Huang (2022), Invertibility of Adjacency Matrices for Random d-Regular Graphs, Duke Mathematical Journal, 170 (18), pp. 3977-4032.
Han Gao, Xu Han, Jiaoyang Huang, Jian-Xun Wang, Liping Liu (2022), PatchGT: Transformer over Non-trainable Clusters for Learning Graph Representations, Proceedings of the First Learning on Graphs Conference, 198 ().
Serban Belinschi, Alice Guionnet, Jiaoyang Huang (2022), Large Deviation Principles via Spherical Integrals, Probability and Mathematical Physics, 3 (3).
Daniel Zhengyu Huang, Jiaoyang Huang, Sebastian Reich, Andrew M Stuart (2022), Efficient Derivative-free Bayesian Inference for Large-Scale Inverse Problems, Inverse Problems, 38 ().
Kenji Kawaguchi, Zhun Deng, Kyle Luh, Jiaoyang Huang (2022), Robustness Implies Generalization via Data-Dependent Generalization Bounds, International Conference on Machine Learning (Long Talk).
Vadim Gorin and Jiaoyang Huang, Dynamical Loop Equation.
Jiaoyang Huang (Working), Edge Statistics for Lozenge Tilings of Polygons, I: Concentration of Height Function on Strip Domains.
Kenji Kawaguchi and Jiaoyang Huang (2021), Gradient Descent Finds Global Minima for Generalizable Deep Neural Networks of Practical Sizes, Proceedings of the 57th Allerton Conference on Communication, Control, and Computing, IEEE.
Amol Aggarwal and Jiaoyang Huang (Working), Edge Statistics for Lozenge Tilings of Polygons, II: Airy Line Ensemble.
All Research from Jiaoyang Huang »

Activity

Latest Research

Kenji Kawaguchi, Zhun Deng, Xu Ji, Jiaoyang Huang (2023), How Does Information Bottleneck Help Deep Learning?, Proceedings of the 40th International Conference on Machine Learning (ICML), 202 ().

All Research

In the News

Five Myths About Generative AI That Leaders Should Know

Experts from Wharton and the “Magnificent Seven” tech companies debunk five misconceptions about gen AI that could stand in the way of implementation.…Read More

Knowledge @ Wharton - 2024/04/30

All News