Elisabetta Cornacchia
7 papers · 2021–2025 · 4 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
🌉
Interdisciplinary Bridge · Silver
🗺️
Taxonomy Completionist
(15)
Venues
Top co-authors
Research topics
Machine Learning
(7)
Optimization & Theory · Machine Learning
(6)
Deep Learning
(3)
Architectures
(3)
Optimization & Theory · Deep Learning
(2)
Artificial Intelligence
(1)
Computer Science
(1)
Mathematics & Optimization
(1)
Application Areas
(1)
Bayesian & Probabilistic · Artificial Intelligence
(1)
Bayesian & Probabilistic · Machine Learning
(1)
Core Methods
(1)
Foundations
(1)
Learning Paradigms
(1)
Learning Types
(1)
Keywords
neural network
(5)
gradient descent
(4)
parity learning
(2)
curriculum learning
(2)
learning theory
(2)
generalization error
(1)
stochastic block model
(1)
gaussian distribution
(1)
boolean function
(1)
broadcasting on tree
(1)
single-index model
(1)
relu network
(1)
neural network initialization
(1)
product distribution
(1)
parity function
(1)
logical function
(1)
random perturbation
(1)
initial alignment
(1)
sparse boolean function
(1)
boolean influence
(1)
Papers
Learning High-Degree Parities: The Crucial Role of the Initialization
ICLR 2025
Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions
COLT 2025
A Mathematical Model for Curriculum Learning for Parities
ICML 2023
Provable Advantage of Curriculum Learning on Parity Targets with Mixed Inputs
NeurIPS 2023
An Initial Alignment between Neural Network and Target is Needed for Gradient Descent to Learn
ICML 2022
Learning to Reason with Neural Networks: Generalization, Unseen Data and Boolean Measures
NeurIPS 2022
Stochastic block model entropy and broadcasting on trees with survey
COLT 2021