On the Universality of the Double Descent Peak in Ridgeless Regression

v1v2v3v4v5v6v7v8 (latest)

On the Universality of the Double Descent Peak in Ridgeless Regression

International Conference on Learning Representations (ICLR), 2020

5 October 2020

David Holzmüller

ArXiv (abs)PDF HTML

Papers citing "On the Universality of the Double Descent Peak in Ridgeless Regression"

9 / 9 papers shown

Title
Models of Heavy-Tailed Mechanistic Universality Liam Hodgkinson Zhichao Wang Michael W. Mahoney 221 3 0 04 Jun 2025
Overparameterized Multiple Linear Regression as Hyper-Curve Fitting E. Atza N. Budko 118 2 0 11 Apr 2024
Mind the spikes: Benign overfitting of kernels and neural networks in fixed dimensionNeural Information Processing Systems (NeurIPS), 2023 Moritz Haas David Holzmüller U. V. Luxburg Ingo Steinwart MLT 286 22 0 23 May 2023
Regularization Trade-offs with Fake FeaturesEuropean Signal Processing Conference (EUSIPCO), 2022 Martin Hellkvist Ayça Özçelikkale Anders Ahlén 305 0 0 01 Dec 2022
Monotonicity and Double Descent in Uncertainty Estimation with Gaussian ProcessesInternational Conference on Machine Learning (ICML), 2022 Liam Hodgkinson Christopher van der Heide Fred Roosta Michael W. Mahoney UQCV 221 7 0 14 Oct 2022
On the Impossible Safety of Large AI Models El-Mahdi El-Mhamdi Sadegh Farhadkhani R. Guerraoui Nirupam Gupta L. Hoang Rafael Pinot Sébastien Rouault John Stephan 285 37 0 30 Sep 2022
A Universal Trade-off Between the Model Size, Test Loss, and Training Loss of Linear PredictorsSIAM Journal on Mathematics of Data Science (SIMODS), 2022 Nikhil Ghosh M. Belkin 262 7 0 23 Jul 2022
Benign, Tempered, or Catastrophic: A Taxonomy of Overfitting Neil Rohit Mallinar James B. Simon Amirhesam Abedsoltan Parthe Pandit M. Belkin Preetum Nakkiran 284 39 0 14 Jul 2022
Data splitting improves statistical performance in overparametrized regimesInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2021 Nicole Mücke Enrico Reiss Jonas Rungenhagen Markus Klein 155 8 0 21 Oct 2021