Seminar
Mathematical Theory of ModelBased Inference from Incomplete Observations
작성자Author
관리자
작성일Date
20171109 14:36
조회Views
483
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 162
일시Date  제목Title  연사Speaker  장소Place 
20180220 
 Horschild homology of DGcategories
수학과

2018.02.13

추천 0

조회 98

KyoungSeog Lee  CGP Hall, PIRL 143 
20180214 
PMI Number Theory Seminar  Some problems for Hecke eigenforms related to Maeda's conjecture
수학과

2018.02.12

추천 0

조회 92

Do Hoon Choi  Math. Bldg. 404 
20180206 
 Introduction to the A∞structure on Fukaya category II
수학과

2018.02.05

추천 0

조회 98

Christophe Wacheux  CGP Hall, PIRL 143 
20180213 
 Introduction to the A∞structure on Fukaya category III
수학과

2018.02.05

추천 0

조회 71

TaeSu Kim  CGP Hall, PIRL 143 
20180130 
IBSCGP Derived Seminar  Introduction to the A∞structure on Fukaya category
수학과

2018.01.29

추천 0

조회 107

Christophe Wacheux  CGP Hall, PIRL 143 
20180131 
IBSCGP Director’s Seminar  Wallcrossing formula
수학과

2018.01.24

추천 0

조회 118

YongGeun Oh  CGP Hall, PIRL 143 
20180122 
GAIA Seminar on Complex Analytic Geometry  DiederichFornaess index and Steinness index
수학과

2018.01.22

추천 0

조회 145

Mr. Jihun Yum  Math. Bldg. 106 
20180118 
IBSCGP Seminar  Ergodic approach to combinatorial number theory
관리자

2018.01.17

추천 0

조회 151

Younghwan Son  CGP Hall, PIRL 143 
20180117 
IBSCGP Seminar  SYZ transforms for immersed Lagrangian multisections
관리자

2018.01.15

추천 0

조회 123

YatHin Suen  CGP Hall, PIRL 143 
20180116 
IBSCGP Derived Seminar  The Bar adjunction II
mujeong

2018.01.14

추천 0

조회 118

Byung Hee An  CGP Hall, PIRL 143 