https://www.math.snu.ac.kr/board/files/attach/images/701/ff97c54e6e21a4ae39315f9a12b27314.png
Extra Form
Lecturer 이창한
Dept. Northwestern University
date Sep 16, 2021

 

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
Attachment '1'
  1. Symplectic topology and mirror symmetry of partial flag manifolds

  2. 돈은 어떻게 우리 삶에 돈며들었는가? (불확실성 시대에 부는 선형적으로 증가하는가?)

  3. <학부생을 위한 ɛ 강연> Mathematics and music: Pythagoras, Bach, Fibonacci and AI

  4. Topological surgery through singularity in mean curvature flow

  5. 17Oct
    by 김수현
    in Math Colloquia

    Heavy-tailed large deviations and deep learning's generalization mystery

  6. Diophantine equations and moduli spaces with nonlinear symmetry

  7. <정년퇴임 기념강연> Hardy, Beurling, and invariant subspaces

  8. <정년퇴임 기념강연> The Elements of Euclid

  9. On circle diffeomorphism groups

  10. <학부생을 위한 ɛ 강연> Symplectic geometry and the three-body problem

  11. WGAN with an Infinitely wide generator has no spurious stationary points

  12. Free boundary problems arising from mathematical finance

  13. One and Two dimensional Coulomb Systems

  14. Ill-posedness for incompressible Euler equations at critical regularit

  15. <정년퇴임 기념강연> 수학의 시대정신(?)

  16. <학부생을 위한 ɛ 강연> Mathematical Aspects of Machine Learning and Deep Learning AI

  17. Lie group actions on symplectic manifolds

  18. Mathematics, Biology and Mathematical Biology

  19. Quantitative residual non-vanishing of special values of various L-functions

  20. Quantum Dynamics in the Mean-Field and Semiclassical Regime

Board Pagination Prev 1 2 3 4 5 6 7 8 9 10 11 12 Next
/ 12