Emanuele Troiani
5 papers · 2024–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
🧭
Keyword Pioneer
🌍
Conference Polyglot
(3)
🐝
Cross-Pollinator
(14)
🌉
Interdisciplinary Bridge
🗺️
Taxonomy Completionist
(11)
Conferences
AISTATS (2)
ICML (2)
NIPS (1)
Top co-authors
Keywords
learning theory
(1)
robust regression
(1)
bayesian inference
(1)
outlier detection
(1)
asymptotic analysis
(1)
message passing
(1)
gradient descent
(1)
approximate message passing
(1)
generalization error
(1)
matrix denoising
(1)
loss function
(1)
test error
(1)
bayes-optimal test error
(1)
quadratic activation
(1)
empirical risk minimisation
(1)
robust linear regression
(1)
neural network
(1)
bayesian optimal
(1)
Papers
Fundamental computational limits of weak learnability in high-dimensional multi-index models
AISTATS 2025
Fundamental limits of learning in sequence multi-index models and deep attention networks: high-dimensional asymptotics and sharp thresholds
ICML 2025
Bayes-optimal learning of an extensive-width neural network from quadratically many samples
NIPS 2024
Asymptotic Characterisation of the Performance of Robust Linear Regression in the Presence of Outliers
AISTATS 2024
The Benefits of Reusing Batches for Gradient Descent in Two-Layer Networks: Breaking the Curse of Information and Leap Exponents
ICML 2024