Least Squares Regression Can Exhibit Under-Parameterized Double Descent

v1v2 (latest)

Least Squares Regression Can Exhibit Under-Parameterized Double Descent

Neural Information Processing Systems (NeurIPS), 2023

24 May 2023

Rishi Sonthalia

ArXiv (abs)PDF HTML

Papers citing "Least Squares Regression Can Exhibit Under-Parameterized Double Descent"

5 / 5 papers shown

Title
Matricial Free Energy as a Gaussianizing Regularizer: Enhancing Autoencoders for Gaussian Code Generation Rishi Sonthalia Raj Rao Nadakuditi 64 0 0 20 Oct 2025
Low Rank Gradients and Where to Find Them Rishi Sonthalia Michael Murray Guido Montúfar 100 2 0 01 Oct 2025
Generalization for Least Squares Regression With Simple Spiked Covariances Jiping Li Rishi Sonthalia 175 1 0 17 Oct 2024
Near-Interpolators: Rapid Norm Growth and the Trade-Off between Interpolation and GeneralizationInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2024 Yutong Wang Rishi Sonthalia Wei Hu 244 7 0 12 Mar 2024
Towards fully covariant machine learning Soledad Villar D. Hogg Weichi Yao George A. Kevrekidis Bernhard Schölkopf AI4CE 255 13 0 31 Jan 2023