Does the Data Induce Capacity Control in Deep Learning?

27 October 2021

Papers citing "Does the Data Induce Capacity Control in Deep Learning?"

9 / 9 papers shown

Title
An Analytical Characterization of Sloppiness in Neural Networks: Insights from Linear Models J. Mao Itay Griniasty Yan Sun M. Transtrum J. Sethna Pratik Chaudhari 24 0 0 13 May 2025
Measuring and Controlling Solution Degeneracy across Task-Trained Recurrent Neural Networks Ann Huang Satpreet H. Singh Kanaka Rajan 19 0 0 04 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 41 2 0 18 Jul 2024
Learning Capacity: A Measure of the Effective Dimensionality of a Model Daiwei Chen Wei-Di Chang Pratik Chaudhari 29 3 0 27 May 2023
The Training Process of Many Deep Networks Explores the Same Low-Dimensional Manifold J. Mao Itay Griniasty H. Teoh Rahul Ramesh Rubing Yang M. Transtrum J. Sethna Pratik Chaudhari 3DPC 39 15 0 02 May 2023
A picture of the space of typical learnable tasks Rahul Ramesh J. Mao Itay Griniasty Rubing Yang H. Teoh M. Transtrum J. Sethna Pratik Chaudhari SSL DRL 36 4 0 31 Oct 2022
Spectral Bias Outside the Training Set for Deep Networks in the Kernel Regime Benjamin Bowman Guido Montúfar 14 14 0 06 Jun 2022
Robust Fine-Tuning of Deep Neural Networks with Hessian-based Generalization Guarantees Haotian Ju Dongyue Li Hongyang R. Zhang 35 28 0 06 Jun 2022
The activity-weight duality in feed forward neural networks: The geometric determinants of generalization Yu Feng Yuhai Tu MLT 75 14 0 21 Mar 2022