Results 231 to 240 of about 368,237 (276)

Benign overfitting in linear regression [PDF]

Proceedings of the National Academy of Sciences of the United States of America, 2020
The phenomenon of benign overfitting is one of the key mysteries uncovered by deep learning methodology: deep neural networks seem to predict well, even with a perfect fit to noisy training data. Motivated by this phenomenon, we consider when a perfect fit to training data in linear regression is compatible with accurate prediction.
Peter L Bartlett, Philip M Long, Gabor Lugosi   +2 more
exaly   +7 more sources

Some of the next articles are maybe not open access.

Related searches:

On Method Overfitting

Journal of Heuristics, 1998
zbMATH Open Web Interface contents unavailable due to conflicting licenses.
openaire   +3 more sources

The Problem of Overfitting

Journal of Chemical Information and Computer Sciences, 2003
AbstractFor Abstract see ChemInform Abstract in Full Text.
openaire   +2 more sources

Lazy Overfitting Control

2013
A machine learning model is said overfit the training data relative to a simpler model if the first model is more accurate on the training data but less accurate on the test data. Overfitting control--selecting an appropriate complexity fit--is a central problem in machine learning.
Armand Prieditis, Stephanie Sapp
openaire   +1 more source

Overfitting

2022
Liangqu Long, Xiangming Zeng
openaire   +2 more sources

Overfitting in portfolio optimization

Journal of Risk Model Validation, 2023
Matteo Maggiolo, Oleg Szehr
openaire   +1 more source

Understanding and combating robust overfitting via input loss landscape analysis and regularization

Pattern Recognition, 2023
Lin Li
exaly  

A systematic review on overfitting control in shallow and deep neural networks

Artificial Intelligence Review, 2021
Mohammad Mahdī Bejani, Mehdi Ghatee
exaly