Federica Gerace
4 papers · 2020–2024 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🗺️
Taxonomy Completionist
(14)
🐣
Hot Topic Early Bird
Venues
Top co-authors
Research topics
Keywords
random feature
(2)
neural network optimization
(2)
statistical learning
(2)
feature learning
(1)
natural language processing
(1)
self-supervised learning
(1)
sample complexity
(1)
computational complexity
(1)
generalization error
(1)
high-dimensional regression
(1)
replica method
(1)
learning dynamics
(1)
higher-order cumulant
(1)
statistical limit
(1)
simplicity bia
(1)
binary neural network
(1)
surrogate network
(1)
neural network
(1)
spiked cumulant model
(1)
double descent
(1)
Papers
A distributional simplicity bias in the learning dynamics of transformers
NeurIPS 2024
Learning from higher-order correlations, efficiently: hypothesis tests, random features, and neural networks
NeurIPS 2024
Critical initialisation in continuous approximations of binary neural networks
ICLR 2020
Generalisation error in learning with random features and the hidden manifold model
ICML 2020