Computation, Statistics, and Optimization of random functions
 
 
Description: 

When faced with a data analysis, learning, or statistical inference problem, the amount and quality of data available fundamentally determines whether such tasks can be performed with certain levels of accuracy. Indeed, many theoretical disciplines study limits of such tasks by investigating whether a dataset effectively contains the information of interest. With the growing size of datasets however, it is crucial not only that the underlying statistical task is possible, but also that is doable by means of efficient algorithms. In this talk we will discuss methods aiming to establish limits of when statistical tasks are possible with computationally efficient methods or when there is a fundamental ``Statistical-to-Computational gap'' in which an inference task is statistically possible but inherently computationally hard.
This is intimately related to understanding the geometry of random functions, with connections to statistical physics, study of spin glasses, random geometry; and in an important example, algebraic invariant theory.

 

There will be a coffee-break at 15:45 (Atrium, level 2).

 

This colloquium is the CIM Colloquium 2020, part of the programme of the annual council of the CIM Associates. It is organized by CIM and sponsored by CMUC.

 

Video archive at https://www.mat.uc.pt/~cmuc/videos/AfonsoBandeira.06.03.20.mp4

 

 

Start Date:  2020-03-06
Start Time:   14:30
Speaker:  Afonso Bandeira (ETH Zurich, Switzerland)
Institution:  ETH Zurich
Place:  Sala Pedro Nunes, Departamento de Matemática da Universidade de Coimbra
Organization:  CIM and CMUC
URL:  http://www.cim.pt/agenda/event/210
See more:   <Main>  
 
Attached Files
 
File Description
Financial Support
One register found.1
© Centre for Mathematics, University of Coimbra, funded by
Science and Technology Foundation
Powered by: rdOnWeb v1.4 | technical support