3 papers
math.PR2025
Variational formula for the logarithmic potential of free additive convolutions
Francesco Concetti, David Belius, Giuseppe Genovese
We establish a general variational formula for the logarithmic potential of the free additive convolution of two compactly supported probability measure on . The formula is giv…
cond-mat.dis-nn2024
Injectivity of ReLU networks: perspectives from statistical physics
Antoine Maillard, Afonso S. Bandeira, David Belius +2
When can the input of a ReLU neural network be inferred from its output? In other words, when is the network injective? We consider a single layer, , w…
cs.LG2024
A Comprehensive Analysis on the Learning Curve in Kernel Ridge Regression
Tin Sum Cheng, Aurelien Lucchi, Anastasis Kratsios +1
This paper conducts a comprehensive study of the learning curves of kernel ridge regression (KRR) under minimal assumptions. Our contributions are three-fold: 1) we analyze the rol…