Whitening and second order optimization both make information in the dataset unusable during training, and can reduce or prevent generalization

17 August 2020

Papers citing "Whitening and second order optimization both make information in the dataset unusable during training, and can reduce or prevent generalization"

4 / 4 papers shown

Title
Effective Learning with Node Perturbation in Multi-Layer Neural Networks Sander Dalm Marcel van Gerven Nasir Ahmad AAML 27 0 0 02 Oct 2023
General-Purpose In-Context Learning by Meta-Learning Transformers Louis Kirsch James Harrison Jascha Narain Sohl-Dickstein Luke Metz 34 72 0 08 Dec 2022
Amortized Proximal Optimization Juhan Bae Paul Vicol Jeff Z. HaoChen Roger C. Grosse ODL 25 14 0 28 Feb 2022
Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10,000-Layer Vanilla Convolutional Neural Networks Lechao Xiao Yasaman Bahri Jascha Narain Sohl-Dickstein S. Schoenholz Jeffrey Pennington 220 348 0 14 Jun 2018