1.3k citations · 1.6k across the 25 of their papers we have counts for
Showing 2024 · stat.MLShow all
2 papers · 2 filters
stat.ML2024
How DNNs break the Curse of Dimensionality: Compositionality and Symmetry Learning
Arthur Jacot, Seok Hoan Choi, Yuxiao Wen
We show that deep neural networks (DNNs) can efficiently learn any composition of functions with bounded -norm, which allows DNNs to break the curse of dimensionality in way…
stat.ML2024
Hamiltonian Mechanics of Feature Learning: Bottleneck Structure in Leaky ResNets
Arthur Jacot, Alexandre Kaiser
We study Leaky ResNets, which interpolate between ResNets and Fully-Connected nets depending on an 'effective depth' hyper-parameter . In the infinite depth limit, we st…