https://www.math.snu.ac.kr/board/files/attach/images/701/ff97c54e6e21a4ae39315f9a12b27314.png
Extra Form
강연자 이창한
소속 Northwestern University
date 2021-09-16

 

Abstract: 
While the typical behaviors of stochastic systems are often deceptively oblivious to the tail distributions of the underlying uncertainties, the ways rare events arise are vastly different depending on whether the underlying tail distributions are light-tailed or heavy-tailed. Roughly speaking, in light-tailed settings, a system-wide rare event arises because everything goes wrong a little bit as if the entire system has conspired up to provoke the rare event (conspiracy principle), whereas, in heavy-tailed settings, a system-wide rare event arises because a small number of components fail catastrophically (catastrophe principle). In the first part of this talk, I will introduce the recent developments in the theory of large deviations for heavy-tailed stochastic processes at the sample path level and rigorously characterize the catastrophe principle. In the second part, I will explore an intriguing connection between the catastrophe principle and a central mystery of modern AI—the unreasonably good generalization performance of deep neural networks.
 
This talk is based on the ongoing research in collaboration with Mihail Bazhba, Jose Blanchet, Bohan Chen, Sewoong Oh, Insuk Seo, Zhe Su, Xingyu Wang, and Bert Zwart.
 
Short Bio: 
Chang-Han Rhee is an Assistant Professor in Industrial Engineering and Management Sciences at Northwestern University. Before joining Northwestern University, he was a postdoctoral researcher in the Stochastics Group at Centrum Wiskunde & Informatica and in Industrial & Systems Engineering and Biomedical Engineering at Georgia Tech. He received his Ph.D. in Computational and Mathematical Engineering from Stanford University. His research interests include applied probability, stochastic simulation, and statistical learning. He was a winner of the Outstanding Publication Award from the INFORMS Simulation Society in 2016, a winner of the Best Student Paper Award (MS/OR focused) at the 2012 Winter Simulation Conference, and a finalist of the 2013 INFORMS George Nicholson Student Paper Competition.
Atachment
첨부 '1'
List of Articles
카테고리 제목 소속 강연자
수학강연회 Root multiplicities of hyperbolic Kac-Moody algebras and Fourier coefficients of modular forms file Univ. of Connecticut 이규환
수학강연회 학부학생을 위한 강연회: 기하학과 우주론 file 홍익대학교 이남훈
수학강연회 Trends to equilibrium in collisional rarefied gas theory file 포항공과대학교 이동현
수학강연회 Mirror symmetry of pairings file 숭실대학교 이상욱
수학강연회 <학부생을 위한 ɛ 강연> Convergence of Fourier series and integrals in Lebesgue spaces file 서울대 이상혁
수학강연회 An introduction to hyperplane arrangements file 서울대 이승진
수학강연회 Creation of concepts for prediction models and quantitative trading file Haafor 이승환
수학강연회 On function field and smooth specialization of a hypersurface in the projective space file KAIST 이용남
수학강연회 Global result for multiple positive radial solutions of p-Laplacian system on exterior domain file 부산대학교 이용훈
수학강연회 <정년퇴임 기념강연> Hardy, Beurling, and invariant subspaces file 서울대학교 이우영
수학강연회 Survey on a geography of model theory file 창원대학교 이정욱
수학강연회 Averaging formula for Nielsen numbers file 서강대학교 이종범
수학강연회 The Mathematics of the Bose Gas and its Condensation file KAIST 이지운
수학강연회 Role of Computational Mathematics and Image Processing in Magnetic Resonance Electrical Impedance Tomography (MREIT) file KAIST 이창옥
수학강연회 Heavy-tailed large deviations and deep learning's generalization mystery file Northwestern University 이창한
수학강연회 Analysis and computations of stochastic optimal control problems for stochastic PDEs file 아주대 이형천
수학강연회 Non-commutative Lp-spaces and analysis on quantum spaces file 서울대학교 이훈희
수학강연회 Alice and Bob meet Banach and von Neumann file 서울대 이훈희
수학강연회 Cloaking via Change of Variables file KAIST 임미경
수학강연회 Volume entropy of hyperbolic buildings file 서울대 임선희
Board Pagination Prev 1 2 3 4 5 6 7 8 9 10 11 12 Next
/ 12