What Can Be Learnt With Wide Convolutional Neural Networks?

1 August 2022

Papers citing "What Can Be Learnt With Wide Convolutional Neural Networks?"

9 / 9 papers shown

Title
Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures Francesco Cagnetta Alessandro Favero Antonio Sclocchi M. Wyart 26 0 0 11 May 2025
Learning curves theory for hierarchically compositional data with power-law distributed features Francesco Cagnetta Hyunmo Kang M. Wyart 36 0 0 11 May 2025
U-Nets as Belief Propagation: Efficient Classification, Denoising, and Diffusion in Generative Hierarchical Models Song Mei 3DV AI4CE DiffM 41 11 0 29 Apr 2024
NTK-Guided Few-Shot Class Incremental Learning Jingren Liu Zhong Ji Yanwei Pang Yunlong Yu CLL 34 3 0 19 Mar 2024
Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Models Guillermo Ortiz-Jiménez Alessandro Favero P. Frossard MoMe 37 103 0 22 May 2023
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
Data-driven emergence of convolutional structure in neural networks Alessandro Ingrosso Sebastian Goldt 48 38 0 01 Feb 2022
Spectrum Dependent Learning Curves in Kernel Regression and Wide Neural Networks Blake Bordelon Abdulkadir Canatar C. Pehlevan 131 200 0 07 Feb 2020
Norm-Based Capacity Control in Neural Networks Behnam Neyshabur Ryota Tomioka Nathan Srebro 116 577 0 27 Feb 2015