Benign, Tempered, or Catastrophic: A Taxonomy of Overfitting

14 July 2022

Papers citing "Benign, Tempered, or Catastrophic: A Taxonomy of Overfitting"

9 / 9 papers shown

Title
Overfitting Behaviour of Gaussian Kernel Ridgeless Regression: Varying Bandwidth or Dimensionality Marko Medvedev Gal Vardi Nathan Srebro 49 3 0 05 Sep 2024
Recite, Reconstruct, Recollect: Memorization in LMs as a Multifaceted Phenomenon USVSN Sai Prashanth Alvin Deng Kyle O'Brien Jyothir S V Mohammad Aflah Khan ... Jacob Ray Fuehne Stella Biderman Tracy Ke Katherine Lee Naomi Saphra 55 12 0 25 Jun 2024
When does compositional structure yield compositional generalization? A kernel theory Samuel Lippl Kim Stachenfeld NAI CoGe 62 5 0 26 May 2024
Do deep neural networks have an inbuilt Occam's razor? Chris Mingard Henry Rees Guillermo Valle Pérez A. Louis UQCV BDL 19 15 0 13 Apr 2023
Strong inductive biases provably prevent harmless interpolation Michael Aerni Marco Milanta Konstantin Donhauser Fanny Yang 25 9 0 18 Jan 2023
Deep Linear Networks can Benignly Overfit when Shallow Ones Do Niladri S. Chatterji Philip M. Long 8 8 0 19 Sep 2022
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
Foolish Crowds Support Benign Overfitting Niladri S. Chatterji Philip M. Long 83 20 0 06 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