A Universal Trade-off Between the Model Size, Test Loss, and Training Loss of Linear Predictors

23 July 2022

Papers citing "A Universal Trade-off Between the Model Size, Test Loss, and Training Loss of Linear Predictors"

9 / 9 papers shown

Title
Feature maps for the Laplacian kernel and its generalizations Sudhendu Ahir Parthe Pandit 60 0 0 24 Feb 2025
Overfitting Behaviour of Gaussian Kernel Ridgeless Regression: Varying Bandwidth or Dimensionality Marko Medvedev Gal Vardi Nathan Srebro 68 3 0 05 Sep 2024
Near-Interpolators: Rapid Norm Growth and the Trade-Off between Interpolation and Generalization Yutong Wang Rishi Sonthalia Wei Hu 46 5 0 12 Mar 2024
More is Better in Modern Machine Learning: when Infinite Overparameterization is Optimal and Overfitting is Obligatory James B. Simon Dhruva Karkada Nikhil Ghosh Mikhail Belkin AI4CE BDL 37 14 0 24 Nov 2023
Noisy Interpolation Learning with Shallow Univariate ReLU Networks Nirmit Joshi Gal Vardi Nathan Srebro 32 8 0 28 Jul 2023
Mind the spikes: Benign overfitting of kernels and neural networks in fixed dimension Moritz Haas David Holzmüller U. V. Luxburg Ingo Steinwart MLT 35 14 0 23 May 2023
Benign Overfitting in Linear Classifiers and Leaky ReLU Networks from KKT Conditions for Margin Maximization Spencer Frei Gal Vardi Peter L. Bartlett Nathan Srebro 30 22 0 02 Mar 2023
Foolish Crowds Support Benign Overfitting Niladri S. Chatterji Philip M. Long 83 20 0 06 Oct 2021
When is Memorization of Irrelevant Training Data Necessary for High-Accuracy Learning? Gavin Brown Mark Bun Vitaly Feldman Adam D. Smith Kunal Talwar 253 93 0 11 Dec 2020