More is Better in Modern Machine Learning: when Infinite Overparameterization is Optimal and Overfitting is Obligatory

24 November 2023

Papers citing "More is Better in Modern Machine Learning: when Infinite Overparameterization is Optimal and Overfitting is Obligatory"

5 / 5 papers shown

Title
High-dimensional Analysis of Knowledge Distillation: Weak-to-Strong Generalization and Scaling Laws M. E. Ildiz Halil Alperen Gozeten Ege Onur Taga Marco Mondelli Samet Oymak 51 2 0 24 Oct 2024
How Feature Learning Can Improve Neural Scaling Laws Blake Bordelon Alexander B. Atanasov C. Pehlevan 49 12 0 26 Sep 2024
The Eigenlearning Framework: A Conservation Law Perspective on Kernel Regression and Wide Neural Networks James B. Simon Madeline Dickens Dhruva Karkada M. DeWeese 40 26 0 08 Oct 2021
Spectrum Dependent Learning Curves in Kernel Regression and Wide Neural Networks Blake Bordelon Abdulkadir Canatar C. Pehlevan 131 199 0 07 Feb 2020
Scaling Laws for Neural Language Models Jared Kaplan Sam McCandlish T. Henighan Tom B. Brown B. Chess R. Child Scott Gray Alec Radford Jeff Wu Dario Amodei 226 4,424 0 23 Jan 2020