Luca Pesce

Joined

May 2022

Names

Luca Pesce (Preferred)

Emails

****@epfl.ch (Confirmed)

****@outlook.it (Confirmed)

Personal Links

Homepage

Google Scholar

DBLP

Career & Education History

PhD student

EPFL - EPF Lausanne (epfl.ch)

2021 – 2025

MS student

Polytechnic Institute of Turin (polito.it)

2019 – 2021

Undergrad student

University of Naples Federico II (unina.it)

2016 – 2019

Advisors, Relations & Conflicts

Coauthor

Lenka Zdeborova

Present

Coauthor

Bruno Loureiro

Present

Coauthor

Ludovic Stephan

Present

Coauthor

Yatin Dandi

Present

Coauthor

Luca Arnaboldi

Present

Coauthor

Yue Lu

Present

Coauthor

Hugo Cui

Present

PhD Advisor

Florent Krzakala

2021 – 2025

Expertise

Statistical Physics

Present

Machine Learning

Present

Publications

The Computational Advantage of Depth in Learning High-Dimensional Hierarchical Targets
Yatin Dandi, Luca Pesce, Lenka Zdeborova, Florent Krzakala
- NeurIPS 2025 spotlight
- Readers: Everyone
A Random Matrix Theory Perspective on the Spectrum of Learned Features and Asymptotic Generalization Capabilities
Yatin Dandi, Luca Pesce, Hugo Cui, Florent Krzakala, Yue Lu, Bruno Loureiro
- AISTATS 2025 Oral
- Readers: Everyone
Repetita Iuvant: Data Repetition Allows SGD to Learn High-Dimensional Multi-Index Functions
Luca Arnaboldi, Yatin Dandi, Florent Krzakala, Luca Pesce, Ludovic Stephan
- HiLD at ICML 2024 Poster
- Readers: Everyone
Asymptotics of feature learning in two-layer networks after one gradient-step
Hugo Cui, Luca Pesce, Yatin Dandi, Florent Krzakala, Yue Lu, Lenka Zdeborova, Bruno Loureiro
- ICML 2024 Spotlight
- Readers: Everyone
Online Learning and Information Exponents: The Importance of Batch size & Time/Complexity Tradeoffs
Luca Arnaboldi, Yatin Dandi, Florent Krzakala, Bruno Loureiro, Luca Pesce, Ludovic Stephan
- ICML 2024 Poster
- Readers: Everyone
The Benefits of Reusing Batches for Gradient Descent in Two-Layer Networks: Breaking the Curse of Information and Leap Exponents
Yatin Dandi, Emanuele Troiani, Luca Arnaboldi, Luca Pesce, Lenka Zdeborova, Florent Krzakala
- ICML 2024 Poster
- Readers: Everyone
How Two-Layer Neural Networks Learn, One (Giant) Step at a Time
Yatin Dandi, Florent Krzakala, Bruno Loureiro, Luca Pesce, Ludovic Stephan
- M3L 2023 Poster
- Readers: Everyone
How Two-Layer Networks Learn, One (Giant) Step at a Time
Yatin Dandi, Florent Krzakala, Bruno Loureiro, Luca Pesce, Ludovic Stephan
- ICLR 2024 Conference Desk Rejected Submission
- Readers: Everyone
Are Gaussian Data All You Need? The Extents and Limits of Universality in High-Dimensional Generalized Linear Estimation
Luca Pesce, Florent Krzakala, Bruno Loureiro, Ludovic Stephan
- ICML 2023 Poster
- Readers: Everyone
Are Gaussian data all you need? Extents and limits of universality in high-dimensional generalized linear estimation
Luca Pesce, Florent Krzakala, Bruno Loureiro, Ludovic Stephan
- 2023 (modified: 16 Apr 2023)
- CoRR 2023
- Readers: Everyone

View all 16 publications

Luca Pesce

Names

Emails

Personal Links

Career & Education History

Advisors, Relations & Conflicts

Expertise

Publications

Co-Authors