activity
20232026
most citedMore is Better in Modern Machine Learning: when Infinite Overparameterization is Optimal and Overfitting is Obligatory

5 citations · 5 across the 3 of their papers we have counts for

collaborators
Showing 2025Show all

1 paper · 1 filter

cs.LG2025

The Features at Convergence Theorem: a first-principles alternative to the Neural Feature Ansatz for how networks learn representations

Enric Boix-Adsera, Neil Mallinar, James B. Simon +1

It is a central challenge in deep learning to understand how neural networks learn representations. A leading approach is the Neural Feature Ansatz (NFA) (Radhakrishnan et al. 2024…