Luca Pesce
7 papers · 2022–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
๐ Conference Polyglot (4) ๐ Interdisciplinary Bridge ๐งญ Keyword Pioneer ๐ Cross-Pollinator (15) โ The Questioner
๐
Trend Setter
Conferences
ICML (4)
AISTATS (1)
JMLR (1)
NIPS (1)
Top co-authors
Research topics
Keywords
high-dimensional statistics
(2)
statistical learning
(1)
learning theory
(1)
feature learning
(1)
sparse principal component analysis
(1)
gradient descent
(1)
approximate message passing
(1)
generalization error
(1)
high-dimensional analysis
(1)
high-dimensional clustering
(1)
state evolution
(1)
phase transition
(1)
generalized linear model
(1)
single-index model
(1)
lazy regime
(1)
batch size
(1)
error analysis
(1)
gaussian universality
(1)
neural network
(1)
generalized linear estimation
(1)
Papers
A Random Matrix Theory Perspective on the Spectrum of Learned Features and Asymptotic Generalization Capabilities
AISTATS 2025
Online Learning and Information Exponents: The Importance of Batch size & Time/Complexity Tradeoffs
ICML 2024
The Benefits of Reusing Batches for Gradient Descent in Two-Layer Networks: Breaking the Curse of Information and Leap Exponents
ICML 2024
How Two-Layer Neural Networks Learn, One (Giant) Step at a Time
JMLR 2024
Asymptotics of feature learning in two-layer networks after one gradient-step
ICML 2024
Are Gaussian Data All You Need? The Extents and Limits of Universality in High-Dimensional Generalized Linear Estimation
ICML 2023
Subspace clustering in high-dimensions: Phase transitions & Statistical-to-Computational gap
NIPS 2022