Extra Form
강연자 이창한
소속 Northwestern University
date 2021-09-16


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.
첨부 '1'
List of Articles
카테고리 제목 소속 강연자
수학강연회 Brownian motion with darning and conformal mappings file University of Washington Zhen-Qing Chen
수학강연회 Anomalous diffusions and fractional order differential equations file University of Washington Zhen-Qing Chen
수학강연회 Gaussian free field and conformal field theory file 서울대학교 강남규
수학강연회 Random conformal geometry of Coulomb gas formalism file 서울대학교 강남규
수학강연회 Conformal field theory in mathematics file 고등과학원 강남규
수학강연회 Periodic orbits in symplectic geometry file 서울대 강정수
수학강연회 <학부생을 위한 ε 강연> Variable-driven sociological research with data innovations file 연세대학교 강정한
특별강연 Irreducible Plane Curve Singularities file 서울대학교 강정혁
수학강연회 Spectral Analysis for the Anomalous Localized Resonance by Plasmonic Structures file 인하대학교 강현배
수학강연회 학부생을 위한 ε 강연회: Mathematics from the theory of entanglement file 서울대학교 계승혁
수학강연회 Topology of configuration spaces on graphs file KAIST 고기형
수학강연회 학부생을 위한 강연회: What is the algebraic number theory? file KAIST 구자경
수학강연회 Solver friendly finite element methods file Oklahoma State Univ. 구자언
수학강연회 <학부생을 위한 ɛ 강연> Continuous-time Portfolio Selection file 아주대학교 금융공학과 구형건
수학강연회 학부생을 위한 강연: A COMBINATORIAL FORMULA FOR INFORMATION FLOW IN A NETWORK file Univ. of Rhode Island/서울대학교 국웅
수학강연회 Combinatorial Laplacians on Acyclic Complexes file 서울대학교 국웅
수학강연회 Contact topology of singularities and symplectic fillings file 순천대학교 권명기
수학강연회 Normal form reduction for unconditional well-posedness of canonical dispersive equations file KAIST 권순식
수학강연회 Freudenthal medal, Klein medal 수상자의 수학교육이론 file 서울대 수학교육과 권오남
수학강연회 Compressible viscous Navier-Stokes flows: Corner singularity, regularity file POSTECH 권재룡
Board Pagination Prev 1 2 3 4 5 6 7 8 9 10 11 12 13 14 Next
/ 14