Elisabetta Cornacchia
7 papers · 2021–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
π§
Keyword Pioneer
π
Conference Polyglot
(4)
π
Cross-Pollinator
(13)
π
Interdisciplinary Bridge
πΊοΈ
Taxonomy Completionist
(11)
Conferences
COLT (2)
ICML (2)
NIPS (2)
ICLR (1)
Top co-authors
Keywords
neural network
(4)
gradient descent
(3)
curriculum learning
(2)
community detection
(1)
survey propagation
(1)
generalization error
(1)
stochastic block model
(1)
boolean function
(1)
relu network
(1)
neural network initialization
(1)
product distribution
(1)
parity function
(1)
logical function
(1)
initial alignment
(1)
boolean influence
(1)
parity learning
(1)
mixed input
(1)
learning theory
(1)
2-layer relu
(1)
stochastic gradient descent
(1)
Papers
Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions
COLT 2025
Learning High-Degree Parities: The Crucial Role of the Initialization
ICLR 2025
A Mathematical Model for Curriculum Learning for Parities
ICML 2023
Provable Advantage of Curriculum Learning on Parity Targets with Mixed Inputs
NIPS 2023
Learning to Reason with Neural Networks: Generalization, Unseen Data and Boolean Measures
NIPS 2022
An Initial Alignment between Neural Network and Target is Needed for Gradient Descent to Learn
ICML 2022
Stochastic block model entropy and broadcasting on trees with survey
COLT 2021