Marco Baity-Jesi
4 papers · 2018–2025 · 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 ↓
🌍
Conference Polyglot · Bronze
🏃
Academic Marathon · Sprint
🐣
Hot Topic Early Bird
🧭
Keyword Pioneer
📈
Trend Setter
Venues
Top co-authors
Research topics
Keywords
class imbalance
(2)
anomaly detection
(1)
convergence analysis
(1)
loss landscape
(1)
deep neural network
(1)
learning curve
(1)
learning dynamics
(1)
training dynamics
(1)
activation function
(1)
gradient-based optimizer
(1)
statistical physics
(1)
network depth
(1)
teacher-student model
(1)
minority class
(1)
per-class gradient normalization
(1)
neural network
(1)
perceptron model
(1)
glassy system
(1)
max-pooling layer
(1)
replica theory
(1)
Papers
Class Imbalance in Anomaly Detection: Learning from an Exactly Solvable Model
AISTATS 2025
Initial Guessing Bias: How Untrained Networks Favor Some Classes
ICML 2024
A Theoretical Analysis of the Learning Dynamics under Class Imbalance
ICML 2023
Comparing Dynamics: Deep Neural Networks versus Glassy Systems
ICML 2018