Seminar
Mathematical Theory of ModelBased Inference from Incomplete Observations
작성자Author
관리자
작성일Date
20171109 14:36
조회Views
49
분야Field  수학과 전임교원 임용후보자공개 세미나  

날짜Date  20171108  시간Time  5:00 ~ 6:30 
장소Place  Math. Bldg. 404  초청자Host  수학과 
연사Speaker  이기륭  소속Affiliation  Georgia Institute of Technology/Research Scientist II 
TOPIC  Mathematical Theory of ModelBased Inference from Incomplete Observations  
소개 및 안내사항Content  Title : Mathematical Theory of ModelBased Inference from Incomplete Observations Abstract : In the era of big data, there are many situations where one has to infer from incomplete observations. The imperfection of available data arises in various forms. In this talk, we focus on the following two scenarios. First, we consider compressed learning of high dimensional data. When the original data in high dimension follow a simple geometric model, statistical learning on compressed features in low dimension provides comparable generalization bound. The restricted isometry property (RIP) preserves the geometry of the underlying model and has been an integral tool for the mathematical theory of compressed learning. We propose generalized notions of sparsity and provide a unified framework for the RIP of structured random measurements given by isotropic group actions. Our results extend the RIP for partial Fourier measurements to a much broader context and identify a sufficient number of group structured measurements for the RIP on generalized sparsity models. We illustrate the main results on an infinite dimensional example, where the sparsity represented by a condition that approximates the total variation. Second, we consider the scenario where the desired information as a time series is accessed as indirect observations through a timeinvariant system with uncertainty. The measurements in this case is given in the form of the convolution with an unknown kernel and the estimation is cast as blind deconvolution. Particularly, we study the mathematical theory of multichannel blind deconvolution where we observe the output of multiple channels that are all excited with the same unknown input source. From these observations, we wish to estimate the source and the impulse responses of each of the channels simultaneously. We show that this problem is wellposed if the channel impulse responses follow a simple geometric model. Under these models, we show how the channel estimates can be found by solving corresponding nonconvex optimization problems. We analyze methods for solving these nonconvex programs, and provide performance guarantees for each. 
전체Total 138
일시Date  제목Title  연사Speaker  장소Place 
20171120 
GAIA Seminar on Complex Analytic Geometry  On the MongeAmpère boundary measure of a bounded hyperconvex
관리자

2017.11.21

추천 0

조회 30

Dr. Ngoc Cuong Nguyen  Math. Bldg. 106 
20171114 
포스텍 석학교수와 함께하는 집중강연 시리즈  The Oldest Problem
관리자

2017.11.13

추천 0

조회 183

John Coates  Math. Bldg. 404 
20171121 
IBSCGP Seminar  Aspects of twisted and differential refinements of Ktheory
관리자

2017.11.13

추천 0

조회 44

Byungdo Park  CGP Hall, PIRL 143 
20171121 
IBSCGP Derived Seminar  Model structure of DGalgebras
관리자

2017.11.13

추천 0

조회 40

Weonmo Lee  CGP Hall, PIRL 143 
20171116 
IBSCGP Seminar  Cubical categories and nerve functors
관리자

2017.11.13

추천 0

조회 33

Brice Le Grignou  CGP Hall, PIRL 143 
20171114 
IBSCGP Seminar  Conformally related Riemannian metrics with nongeneric holonomy
관리자

2017.11.13

추천 0

조회 29

Andrei Moroianu  CGP Hall, PIRL 143 
20171114 
IBSCGP Derived Seminar  Homotopy algebras II
관리자

2017.11.13

추천 0

조회 39

Christophe Wacheux  CGP Hall, PIRL 143 
20171113 
IBSCGP Seminar  Classification results on fixed points of symplectic and Hamiltonian circle actions
관리자

2017.11.13

추천 0

조회 30

Donghoon Jang  CGP Hall, PIRL 143 
20171130 
수리응용센터 산업수학 특강  반도체 설비/공정에서의 Data 분석 기술 활용
관리자

2017.11.13

추천 0

조회 30

김태훈  Math. Bldg. 404 
20171116 
수리응용센터 응용수학 세미나  Nonlocal Models for Cellular Adhesion
관리자

2017.11.13

추천 0

조회 45

Thosmas Hillen  Math. Bldg. 404 