April 24: Seminar – Yongdai Kim

Time and Location: 3-4pm in CH 212

Speaker: Yongdai Kim (Seoul National University, Korea)

Title: Fast learning with deep learning architectures for classification

Abstract: We derive the fast convergence rates of a deep neural network (DNN) classifier with the rectified linear unit (ReLU) activation function learned using the hinge loss. We consider three cases for a true model: (1) a smooth decision boundary, (2) smooth conditional class probability, and (3) the margin condition (i.e., the probability of inputs near the decision boundary is small). We show that the DNN classifier learned using the hinge loss achieves fast convergence rates for all three cases provided that the architecture (i.e., the number of layers, number of nodes and sparsity) is carefully selected. An important implication is that DNN architectures are very flexible for use in various cases without much modification. In addition, we consider a DNN classifier learned by minimizing the cross-entropy, and give conditions for fast convergence rates. If time is allowed, computational algorithms to achieve a right size of deep architectures for fast convergence rates is discussed.

This is joint work with Ph.D. students Ilsang Ohn and Dongha Kim.

8750.01 Reading Group in Autumn 2018

Statistical Learning and Data Mining reading group will meet this semester. Regular meetings are scheduled every other Tuesday starting from September 4th from 12:30 to 1:30 pm in Cockins Hall Room 212.

Students may register for course credit by enrolling in STAT 8750.01 – Research Group in Statistical Learning and Data Mining. If you want to be added to the reading group email list, contact Chenxi Zhou at