Humboldt-Universität zu Berlin - Mathematisch-Naturwissenschaftliche Fakultät - Workshop

Schedule

 

High-Dimensional Covariance Operators and their Applications

 

Abstracts

 

Thursday, September 12

09:40-10:20 Welcome & Coffee
10:20-11:10

Angelika Rohde

Bootstrapping linear spectral statistics of high-dimensional
covariance matrices

11:10-12:00 

Stanislav Minsker

Moment inequalities for matrix-valued U-statistics of order 2

12:00-14:00 Lunch Break
14:00-14:50

Radosław Adamczak

The Hanson-Wright inequality in Banach spaces

14:50-15:40

Sean O'Rourke

Eigenvalues and eigenspaces under random perturbation

15:40-16:10 Coffee Break
16:10-17:00

Alexander Meister

Nonparametric estimation of the ability density
in the mixed-effect Rasch model

17:00-17:50

Boaz Nadler

Robust sparse covariance estimation
for elliptical data by thresholding Tyler's M-estimator

19:00-

Workshop Dinner (Via Nova 2, Universitätsstraße 2, 10117 Berlin)

 

Friday, September 13

09:00-09:50

Mikhail Belkin

Modern machine learning and kernel machines

09:50-10:40

Holger Kösters

Sample Eigenstructure: A Random Matrix Perspective

10:40-11:10 Coffee Break
11:10-12:00

Victor Panaretos

Procrustes metrics and optimal transport
of covariance operators

12:00-14:00 Lunch Break
14:00-14:50

Francis Bach

Statistical optimality of stochastic gradient descent on
hard learning problems through multiple passes

14:50-15:40

Matthias Löffler

Linear functionals in PCA and spectral clustering

15:40-16:10 Coffee Break
16:10-17:00

Sjoerd Dirksen

Random hyperplane tessellations and robust
one-bit compressed sensing

17:00-17:50

Thomas Mikosch

Extreme value theory for the entries
of the sample covariance matrix

17:50-

Buffet