Francesca Mignacco
5 papers · 2020–2025 · 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
🏃
Academic Marathon · Sprint
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(12)
Venues
Top co-authors
Research topics
Machine Learning
(5)
Optimization & Theory · Machine Learning
(4)
Deep Learning
(3)
Core Methods
(3)
Optimization & Theory · Deep Learning
(2)
Techniques
(2)
Mathematics & Optimization
(1)
Architectures
(1)
Bayesian & Probabilistic
(1)
Learning Types · Deep Learning
(1)
Learning Types · Machine Learning
(1)
Statistics
(1)
Keywords
neural network training
(2)
gaussian mixture
(2)
stochastic gradient descent
(1)
bayesian learning
(1)
logistic regression
(1)
attention mechanism
(1)
ridge regression
(1)
network pruning
(1)
loss landscape
(1)
generalization error
(1)
high-dimensional analysis
(1)
biological plausibility
(1)
kernel combination
(1)
learning dynamics
(1)
control theory
(1)
attention head
(1)
multi-head self-attention
(1)
statistical mechanics
(1)
self-attention network
(1)
attention path
(1)
Papers
Optimal Protocols for Continual Learning via Statistical Physics and Control Theory
ICLR 2025
Dissecting the Interplay of Attention Paths in a Statistical Mechanics Theory of Transformers
NeurIPS 2024
Forward Learning with Top-Down Feedback: Empirical and Analytical Characterization
ICLR 2024
Dynamical mean-field theory for stochastic gradient descent in Gaussian mixture classification
NeurIPS 2020
The Role of Regularization in Classification of High-dimensional Noisy Gaussian Mixture
ICML 2020