Publisher
source

École Normale Supérieure

PhD Position in Theoretical Machine Learning (Neural Network Learning Theory) École Normale Supérieure in France

Degree Level

PhD

Field of study

Computer Science

Funding

Available

Deadline

Sep 4, 2026

Country flag

Country

France

University

École Normale Supérieure

Social connections

How do I apply for this?

Sign in for free to reveal details, requirements, and source links.

Suggested positions

Keywords

Computer Science
Deep Learning
Mathematics
Riemannian Geometry
Generative Modeling
Statistics

About this position

Applications are invited for a full-time, 36-month PhD position in theoretical machine learning at École Normale Supérieure (ENS - PSL) in Paris, hosted by the Centre Sciences des Données (CSD) within the Département d’Informatique / DI-ENS.

The project focuses on developing a new theoretical framework to understand feature learning and parameter dynamics in artificial neural networks. The research will draw on Riemannian geometry and information geometry to study learning regimes in deep neural networks, with applications in NeuroAI and broader biological data settings.

The position is funded by a French National Research Agency (ANR) grant. The research environment is described as highly collaborative and world-class, with access to high-performance computing resources, including the Jean-Zay supercomputer, as well as regular seminars, mentorship support, and opportunities to co-mentor Master’s students.

Supervision: Arthur Pellegrino (PI, AI Fellow at ENS/PR[AI]RIE) and co-supervision by Bruno Loureiro (HDR, CNRS / DI-ENS).

Candidate profile: Applicants should hold a Master’s degree or equivalent in theoretical machine learning, mathematics, physics, computer science, or another related quantitative field. Strong preparation in linear algebra, multivariable calculus, and probability theory is required; background in differential geometry or dynamical systems is a plus. Practical experience with Python and deep learning frameworks such as PyTorch or JAX is expected, together with strong motivation for fundamental AI research.

Application: Interested candidates should apply by email to [email protected] with a CV (including publications), undergraduate and Master’s transcripts, and a one-page cover letter focused on research interests.

Deadline: 4 September 2026, 23:59 (Europe/Paris). The expected start date is Autumn 2026 / 1 August 2026 listed in the posting metadata.

Funding details

Available

What's required

Master’s degree or equivalent in theoretical machine learning, mathematics, physics, computer science, or a related quantitative field. Strong foundations in linear algebra, multivariable calculus, and probability theory are required; familiarity with differential geometry or dynamical systems theory is a strong plus. Applicants should have proficiency in Python and modern deep learning frameworks such as PyTorch or JAX, and demonstrate high motivation for foundational research in AI theory and its applications.

Ask ApplyKite AI

Start chatting
Can you summarize this position?
What qualifications are required for this position?
How should I prepare my application?