Statistical physics of deep learning

Position: Research appointment (pre-doc) Institute: Uni. Turin
Posted on: 19/05/2026 Deadline: 09/06/2026

Scientific-Disciplinary Group

02/PHYS-02 - Theoretical Physics Of Fundamental Interactions, Models, Mathematical Methods And Applications, 02/PHYS-06 - Physics For Life Sciences, Environment, And Cultural Heritage, Physics Education And History Of Physics

Description

The project aims to understand the mechanisms of generalization in deep learning using tools from statistical physics. The goal is to develop phenomenological, simplified yet quantitative models that describe the interplay between learning algorithms, data structure, and neural network architectures, strongly informed by empirical observations. Using controlled settings and standard model architectures, we will investigate how and under which conditions learning algorithms select specific solutions among many equivalent ones, thereby inducing implicit biases that are crucial for generalization.The methodology combines quantitative experimentation with mathematical descriptions typical of statistical physics, in order to characterize learning dynamics and the properties of the resulting solutions. The results will contribute to a theoretical understanding of deep learning and may, in the longer term, guide the development of more efficient and robust methods.

Compensation

37,808 Euro

Number of positions

1

Maximum duration

12.0

Funding body

Università di Torino

Selection process

Click to expand
Per Titoli. La domanda deve essere presentata tramite la procedura online https://pica.cineca.it/unito/sdn-2026-iii - per informazioni: incarichiricerca@unito.it Mandatory requirement for admission to the selection: italian Laurea Magistrale, or Laurea a Ciclo Unico, or an equivalent degree from foreign Universities, obtained no more than 6 years prior to the application deadline (i.e obtained after 09/06/2020). The Call for Applications (published on the University Bulletin Board under ref. no. 2560 of 19/05/2026), containing the procedures to participate in the selection process and the specific requirements for each selection, is available at https://webapps.unito.it/albo_ateneo/ .