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 Symplectic topology and mirror symmetry of partial flag manifolds file 부산대학교 수학과 김유식
수학강연회 돈은 어떻게 우리 삶에 돈며들었는가? (불확실성 시대에 부는 선형적으로 증가하는가?) file 농협은행 홍순옥
수학강연회 <학부생을 위한 ɛ 강연> Mathematics and music: Pythagoras, Bach, Fibonacci and AI file 피아니스트 임현정
수학강연회 Topological surgery through singularity in mean curvature flow file 고등과학원 최경수
수학강연회 Heavy-tailed large deviations and deep learning's generalization mystery file Northwestern University 이창한
수학강연회 Diophantine equations and moduli spaces with nonlinear symmetry file 서울대학교 황준호
수학강연회 <정년퇴임 기념강연> Hardy, Beurling, and invariant subspaces file 서울대학교 이우영
수학강연회 <정년퇴임 기념강연> The Elements of Euclid file 서울대/광주과학기술원 김홍종
수학강연회 On circle diffeomorphism groups file 고등과학원 김상현
수학강연회 <학부생을 위한 ɛ 강연> Symplectic geometry and the three-body problem file 서울대학교 Otto van Koert
수학강연회 WGAN with an Infinitely wide generator has no spurious stationary points file 서울대학교 류경석
수학강연회 Free boundary problems arising from mathematical finance file 경희대학교 전준기
수학강연회 One and Two dimensional Coulomb Systems file 카이스트 폴정
수학강연회 Ill-posedness for incompressible Euler equations at critical regularit file 서울대학교 정인지
수학강연회 <정년퇴임 기념강연> 수학의 시대정신(?) file 서울대학교 수리과학부 김명환
수학강연회 <학부생을 위한 ɛ 강연> Mathematical Aspects of Machine Learning and Deep Learning AI file 서울대학교 컴퓨터공학부 장병탁
수학강연회 Lie group actions on symplectic manifolds file 성균관대학교 수학교육과 조윤형
수학강연회 Mathematics, Biology and Mathematical Biology file 부산대학교 수학과 정일효
수학강연회 Quantitative residual non-vanishing of special values of various L-functions file UNIST 선해상
수학강연회 Quantum Dynamics in the Mean-Field and Semiclassical Regime file Ecole Polytechnique Francoise Golse
Board Pagination Prev 1 2 3 4 5 6 7 8 9 10 11 12 Next
/ 12