Francesco Cagnetta
6 papers · 2021–2025 · 2 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 ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (17) 🐣 Hot Topic Early Bird 🔥 Unstoppable · Bronze
❓
The Questioner
Venues
Top co-authors
Research topics
Deep Learning
(5)
Machine Learning
(5)
Optimization & Theory · Machine Learning
(5)
Learning Types · Deep Learning
(3)
Interdisciplinary
(2)
Architectures
(2)
Core Methods
(2)
Linguistics
(2)
Models
(2)
Optimization & Theory · Deep Learning
(2)
Artificial Intelligence
(1)
Natural Language Processing
(1)
Core AI
(1)
Generation
(1)
Learning Types · Machine Learning
(1)
Keywords
generalization error
(2)
probabilistic context-free grammar
(2)
convolutional neural network
(2)
learning curve
(2)
sparse representation
(1)
self-supervised learning
(1)
sample complexity
(1)
compositional generalization
(1)
kernel regression
(1)
hierarchical structure
(1)
diffusion model
(1)
language model
(1)
random feature
(1)
next-token prediction
(1)
infinite width
(1)
lazy training
(1)
spatial scale adaptation
(1)
kernel methods
(1)
neural network
(1)
hierarchical composition
(1)
Papers
How Compositional Generalization and Creativity Improve as Diffusion Models are Trained
ICML 2025
Learning curves theory for hierarchically compositional data with power-law distributed features
ICML 2025
Towards a theory of how the structure of language is acquired by deep neural networks
NeurIPS 2024
What Can Be Learnt With Wide Convolutional Neural Networks?
ICML 2023
Learning sparse features can lead to overfitting in neural networks
NeurIPS 2022
Locality defeats the curse of dimensionality in convolutional teacher-student scenarios
NeurIPS 2021