How DNNs break the Curse of Dimensionality: Compositionality and Symmetry Learning

8 July 2024

Papers citing "How DNNs break the Curse of Dimensionality: Compositionality and Symmetry Learning"

6 / 6 papers shown

Title
Shallow diffusion networks provably learn hidden low-dimensional structure Nicholas M. Boffi Arthur Jacot Stephen Tu Ingvar M. Ziemann DiffM 29 1 0 15 Oct 2024
Which Frequencies do CNNs Need? Emergent Bottleneck Structure in Feature Learning Yuxiao Wen Arthur Jacot 45 6 0 12 Feb 2024
Implicit Bias of Large Depth Networks: a Notion of Rank for Nonlinear Functions Arthur Jacot 34 24 0 29 Sep 2022
On the inability of Gaussian process regression to optimally learn compositional functions M. Giordano Kolyan Ray Johannes Schmidt-Hieber 31 12 0 16 May 2022
The Role of Linear Layers in Nonlinear Interpolating Networks Greg Ongie Rebecca Willett 46 15 0 02 Feb 2022
Norm-Based Capacity Control in Neural Networks Behnam Neyshabur Ryota Tomioka Nathan Srebro 111 577 0 27 Feb 2015