English
Related papers

Related papers: Double Descent Risk and Volume Saturation Effects:…

200 papers

A regression model with more parameters than data points in the training data is overparametrized and has the capability to interpolate the training data. Based on the classical bias-variance tradeoff expressions, it is commonly assumed…

Machine Learning · Computer Science 2023-04-18 Tomas McKelvey

Temporal Difference (TD) algorithms are widely used in Deep Reinforcement Learning (RL). Their performance is heavily influenced by the size of the neural network. While in supervised learning, the regime of over-parameterization and its…

Machine Learning · Computer Science 2024-02-20 David Brellmann , Eloïse Berthier , David Filliat , Goran Frehse

In this paper, we studied two identically-trained neural networks (i.e. networks with the same architecture, trained on the same dataset using the same algorithm, but with different initialization) and found that their outputs discrepancy…

Machine Learning · Computer Science 2023-05-26 Yifan Luo , Bin Dong

Unlike the conventional wisdom in statistical learning theory, the test error of a deep neural network (DNN) often demonstrates double descent: as the model complexity increases, it first follows a classical U-shaped curve and then shows a…

Machine Learning · Computer Science 2021-06-04 Xiao Zhang , Dongrui Wu , Haoyi Xiong , Bo Dai

Epoch-wise double descent is the phenomenon where generalisation performance improves beyond the point of overfitting, resulting in a generalisation curve exhibiting two descents under the course of learning. Understanding the mechanisms…

Machine Learning · Statistics 2024-09-20 Amanda Olmin , Fredrik Lindsten

We study generalised linear regression and classification for a synthetically generated dataset encompassing different problems of interest, such as learning with random features, neural networks in the lazy training regime, and the hidden…

Statistics Theory · Mathematics 2022-03-28 Federica Gerace , Bruno Loureiro , Florent Krzakala , Marc Mézard , Lenka Zdeborová

Recent works demonstrated the existence of a double-descent phenomenon for the generalization error of neural networks, where highly overparameterized models escape overfitting and achieve good test performance, at odds with the standard…

Machine Learning · Computer Science 2024-04-02 Elizaveta Demyanenko , Christoph Feinauer , Enrico M. Malatesta , Luca Saglietti

Acquisition of data is a difficult task in many applications of machine learning, and it is only natural that one hopes and expects the population risk to decrease (better performance) monotonically with increasing data points. It turns…

Machine Learning · Computer Science 2022-01-19 Zakaria Mhammedi

We study generalization properties of random features (RF) regression in high dimensions optimized by stochastic gradient descent (SGD) in under-/over-parameterized regime. In this work, we derive precise non-asymptotic error bounds of RF…

Machine Learning · Statistics 2022-10-18 Fanghui Liu , Johan A. K. Suykens , Volkan Cevher

We consider a model for logistic regression where only a subset of features of size $p$ is used for training a linear classifier over $n$ training samples. The classifier is obtained by running gradient descent (GD) on logistic loss. For…

Machine Learning · Statistics 2020-05-12 Zeyu Deng , Abla Kammoun , Christos Thrampoulidis

We provide (high probability) bounds on the condition number of random feature matrices. In particular, we show that if the complexity ratio $\frac{N}{m}$ where $N$ is the number of neurons and $m$ is the number of data samples scales like…

Machine Learning · Statistics 2021-11-08 Zhijun Chen , Hayden Schaeffer

We observe a novel 'multiple-descent' phenomenon during the training process of LSTM, in which the test loss goes through long cycles of up and down trend multiple times after the model is overtrained. By carrying out asymptotic stability…

Machine Learning · Computer Science 2025-05-27 Wenbo Wei , Nicholas Chong Jia Le , Choy Heng Lai , Ling Feng

Overparametrized models can exhibit an excellent generalization performance, although they should be prone to overfitting according to classical statistical theory. The discovery of the "double descent", indicating that the generalization…

Machine Learning · Computer Science 2026-05-22 Tino Werner

From the sampling of data to the initialisation of parameters, randomness is ubiquitous in modern Machine Learning practice. Understanding the statistical fluctuations engendered by the different sources of randomness in prediction is…

Machine Learning · Statistics 2022-10-03 Bruno Loureiro , Cédric Gerbelot , Maria Refinetti , Gabriele Sicuro , Florent Krzakala

Modern deep learning models employ considerably more parameters than required to fit the training data. Whereas conventional statistical wisdom suggests such models should drastically overfit, in practice these models generalize remarkably…

Machine Learning · Statistics 2020-08-18 Ben Adlam , Jeffrey Pennington

Recent evidence has shown the existence of a so-called double-descent and even triple-descent behavior for the generalization error of deep-learning models. This important phenomenon commonly appears in implemented neural network…

Machine Learning · Computer Science 2021-10-25 Antoine Bodin , Nicolas Macris

We investigate the asymptotic risk of a general class of overparameterized likelihood models, including deep models. The recent empirical success of large-scale models has motivated several theoretical studies to investigate a scenario…

Machine Learning · Statistics 2021-03-16 Ryumei Nakada , Masaaki Imaizumi

Understanding how feature learning affects generalization is among the foremost goals of modern deep learning theory. Here, we study how the ability to learn representations affects the generalization performance of a simple class of…

Machine Learning · Computer Science 2022-06-17 Jacob A. Zavatone-Veth , William L. Tong , Cengiz Pehlevan

Training loss and accuracy are the standard signals used to monitor generalization during deep neural network training. Two well-documented phenomena complicate this picture: in grokking, train loss falls rapidly while test performance…

Machine Learning · Computer Science 2026-05-29 Chi-Ning Chou , Oscar Uzdelewicz , Neng-Chun Chiu , Yao-Yuan Yang , SueYeon Chung

Large language models (LLMs) generalize smoothly across continuous semantic spaces, yet strict logical reasoning demands the formation of discrete decision boundaries. Prevailing theories relying on linear isometric projections fail to…

Machine Learning · Computer Science 2026-03-26 Long Zhang , Dai-jun Lin , Wei-neng Chen