Rethinking Information-theoretic Generalization: Loss Entropy Induced PAC Bounds
Invited Talk, Integreat Discrepancies Seminar Series, Integreat, Norway
Talks and Presentations
Understanding the Generalization Ability of Deep Learning Algorithms: A Kernelized Rényi’s Entropy Perspective
Invited Talk, China Symposium on Machine Learning and Applications, Nanjing, China
Understanding the Generalization Ability of Deep Learning Algorithms: A Kernelized Rényi’s Entropy Perspective
Conference Talk, International Joint Conference on Artificial Intelligence, Macao, S.A.R
Optimal Randomized Approximations for Matrix-based Rényi’s Entropy
Poster, Vision and Learning Seminar, Wuxi, China
Robust and Fast Measure of Information via Low-Rank Representation
Conference Talk, AAAI Conference on Artificial Intelligence, Washington, D.C., USA