The Training Process of Many Deep Networks Explores the Same Low-Dimensional Manifold

2 May 2023

Papers citing "The Training Process of Many Deep Networks Explores the Same Low-Dimensional Manifold"

6 / 6 papers shown

Title
An Analytical Characterization of Sloppiness in Neural Networks: Insights from Linear Models Jialin Mao Itay Griniasty Yan Sun Mark K. Transtrum James P. Sethna Pratik Chaudhari 26 0 0 13 May 2025
Density estimation with LLMs: a geometric investigation of in-context learning trajectories Toni J. B. Liu Nicolas Boullé Raphael Sarfati Christopher Earls 30 0 0 07 Oct 2024
Many Perception Tasks are Highly Redundant Functions of their Input Data Rahul Ramesh Anthony Bisulco Ronald W. DiTullio Linran Wei Vijay Balasubramanian Kostas Daniilidis Pratik Chaudhari 44 2 0 18 Jul 2024
A picture of the space of typical learnable tasks Rahul Ramesh Jialin Mao Itay Griniasty Rubing Yang H. Teoh Mark K. Transtrum James P. Sethna Pratik Chaudhari SSL DRL 36 5 0 31 Oct 2022
Patches Are All You Need? Asher Trockman J. Zico Kolter ViT 225 402 0 24 Jan 2022
Bag of Tricks for Image Classification with Convolutional Neural Networks Tong He Zhi-Li Zhang Hang Zhang Zhongyue Zhang Junyuan Xie Mu Li 221 1,399 0 04 Dec 2018