Optimal ridge penalty for real-world high-dimensional data can be zero or negative due to the implicit ridge regularization

28 May 2018

Papers citing "Optimal ridge penalty for real-world high-dimensional data can be zero or negative due to the implicit ridge regularization"

12 / 12 papers shown

Title
Learning the Regularization Strength for Deep Fine-Tuning via a Data-Emphasized Variational Objective Ethan Harvey Mikhail Petrov Michael C. Hughes 45 0 0 28 Jan 2025
General Loss Functions Lead to (Approximate) Interpolation in High Dimensions Kuo-Wei Lai Vidya Muthukumar 26 5 0 13 Mar 2023
Deep Linear Networks can Benignly Overfit when Shallow Ones Do Niladri S. Chatterji Philip M. Long 20 8 0 19 Sep 2022
Target alignment in truncated kernel ridge regression Arash A. Amini R. Baumgartner Dai Feng 14 3 0 28 Jun 2022
A Farewell to the Bias-Variance Tradeoff? An Overview of the Theory of Overparameterized Machine Learning Yehuda Dar Vidya Muthukumar Richard G. Baraniuk 29 71 0 06 Sep 2021
Interpolation can hurt robust generalization even when there is no noise Konstantin Donhauser Alexandru cTifrea Michael Aerni Reinhard Heckel Fanny Yang 31 14 0 05 Aug 2021
Slow-Growing Trees Philippe Goulet Coulombe 31 1 0 02 Mar 2021
Understanding Double Descent Requires a Fine-Grained Bias-Variance Decomposition Ben Adlam Jeffrey Pennington UD 37 93 0 04 Nov 2020
Random Features for Kernel Approximation: A Survey on Algorithms, Theory, and Beyond Fanghui Liu Xiaolin Huang Yudong Chen Johan A. K. Suykens BDL 39 172 0 23 Apr 2020
Exact expressions for double descent and implicit regularization via surrogate random design Michal Derezinski Feynman T. Liang Michael W. Mahoney 18 77 0 10 Dec 2019
A Model of Double Descent for High-dimensional Binary Linear Classification Zeyu Deng A. Kammoun Christos Thrampoulidis 34 144 0 13 Nov 2019
The generalization error of random features regression: Precise asymptotics and double descent curve Song Mei Andrea Montanari 47 626 0 14 Aug 2019