Mathematics, Physics & Machine Learning Seminar   RSS

Afonso Bandeira 04/06/2020, 17:30 — 18:30 — Online
, ETH Zurich

Computation, Statistics, and Optimization of random functions

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.

See also


The IST seminar series Mathematics, Physics & Machine Learning aims at bringing together mathematicians and physicists interested in machine learning (ML) with  ML and AI experts interested in mathematics and physics, with the goals of introducing innovative mathematics and physics-inspired techniques in ML and, reciprocally, applying ML to problems in mathematics and physics.

Organizers: Cláudia Nunes (DM and CEMAT), Cláudia Soares (DEEC and ISR), Francisco Melo (DEI and INESC-ID), João Seixas (DF and CEFEMA), João Xavier (DEEC and ISR), José Mourão (DM and CAMGSD), Mário Figueiredo (DEEC and IT), Pedro Alexandre Santos (DM and INESC-ID)  and Yasser Omar (DM and IT).
Zoom password: distributed with email announcements or send an email to the organizers asking for it.