English
Related papers

Related papers: Towards Understanding Epoch-wise Double descent in…

200 papers

The phenomenon of model-wise double descent, where the test error peaks and then reduces as the model size increases, is an interesting topic that has attracted the attention of researchers due to the striking observed gap between theory…

Machine Learning · Computer Science 2023-12-08 Chris Yuhao Liu , Jeffrey Flanigan

We propose that learning in deep neural networks proceeds in two phases: a rapid curve fitting phase followed by a slower compression or coarse graining phase. This view is supported by the shared temporal structure of three phenomena:…

High Energy Physics - Theory · Physics 2025-07-28 Robert de Mello Koch , Animik Ghosh

Classical learning theory describes a well-characterised U-shaped relationship between model complexity and prediction error, reflecting a transition from underfitting in underparameterised regimes to overfitting as complexity grows. Recent…

Machine Learning · Computer Science 2025-10-01 Guillermo Comesaña Cimadevila

This paper investigates the double descent phenomenon in two-layer neural networks, focusing on the role of L1 regularization and representation dimensions. It explores an alternative double descent phenomenon, named sparse double descent.…

Machine Learning · Computer Science 2024-01-22 Ya Shi Zhang

Generalization of deep neural networks remains one of the main open problems in machine learning. Previous theoretical works focused on deriving tight bounds of model complexity, while empirical works revealed that neural networks exhibit…

Machine Learning · Computer Science 2022-01-31 James Wang , Cheng-Lin Yang

Neural networks appear to have mysterious generalization properties when using parameter counting as a proxy for complexity. Indeed, neural networks often have many more parameters than there are data points, yet still provide good…

Machine Learning · Computer Science 2020-05-26 Wesley J. Maddox , Gregory Benton , Andrew Gordon Wilson

A recent line of research has highlighted the existence of a "double descent" phenomenon in deep learning, whereby increasing the number of training examples $N$ causes the generalization error of neural networks to peak when $N$ is of the…

Machine Learning · Computer Science 2022-01-12 Stéphane d'Ascoli , Levent Sagun , Giulio Biroli

We show that a variety of modern deep learning tasks exhibit a "double-descent" phenomenon where, as we increase model size, performance first gets worse and then gets better. Moreover, we show that double descent occurs not just as a…

Machine Learning · Computer Science 2019-12-06 Preetum Nakkiran , Gal Kaplun , Yamini Bansal , Tristan Yang , Boaz Barak , Ilya Sutskever

The risk of overparameterized models, in particular deep neural networks, is often double-descent shaped as a function of the model size. Recently, it was shown that the risk as a function of the early-stopping time can also be…

Machine Learning · Computer Science 2022-06-06 Fatih Furkan Yilmaz , Reinhard Heckel

The double descent curve is one of the most intriguing properties of deep neural networks. It contrasts the classical bias-variance curve with the behavior of modern neural networks, occurring where the number of samples nears the number of…

Machine Learning · Computer Science 2021-07-05 John Chen , Qihan Wang , Anastasios Kyrillidis

The theory of bias-variance used to serve as a guide for model selection when applying Machine Learning algorithms. However, modern practice has shown success with over-parameterized models that were expected to overfit but did not. This…

Machine Learning · Computer Science 2022-11-21 Luis Sa-Couto , Jose Miguel Ramos , Miguel Almeida , Andreas Wichert

A recent line of work has shown remarkable behaviors of the generalization error curves in simple learning models. Even the least-squares regression has shown atypical features such as the model-wise double descent, and further works have…

Machine Learning · Statistics 2022-12-20 Antoine Bodin , Nicolas Macris

People usually believe that network pruning not only reduces the computational cost of deep networks, but also prevents overfitting by decreasing model capacity. However, our work surprisingly discovers that network pruning sometimes even…

Machine Learning · Computer Science 2022-06-20 Zheng He , Zeke Xie , Quanzhi Zhu , Zengchang Qin

Understanding the inductive bias and generalization properties of large overparametrized machine learning models requires to characterize the dynamics of the training algorithm. We study the learning dynamics of large two-layer neural…

Machine Learning · Statistics 2025-10-30 Andrea Montanari , Pierfrancesco Urbani

Recently, the benefit of heavily overparameterized models has been observed in machine learning tasks: models with enough capacity to easily cross the \emph{interpolation threshold} improve in generalization error compared to the classical…

High Energy Physics - Experiment · Physics 2025-09-03 Matthias Vigl , Lukas Heinrich

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

Graph neural networks (GNNs) excel in modeling relational data such as biological, social, and transportation networks, but the underpinnings of their success are not well understood. Traditional complexity measures from statistical…

Machine Learning · Computer Science 2024-01-24 Cheng Shi , Liming Pan , Hong Hu , Ivan Dokmanić

Recent studies observed a surprising concept on model test error called the double descent phenomenon, where the increasing model complexity decreases the test error first and then the error increases and decreases again. To observe this,…

Machine Learning · Statistics 2025-05-14 Chathurika S Abeykoon , Aleksandr Beknazaryan , Hailin Sang

Deep learning models, particularly Transformers, have achieved impressive results in various domains, including time series forecasting. While existing time series literature primarily focuses on model architecture modifications and data…

Machine Learning · Computer Science 2023-12-01 Valentino Assandri , Sam Heshmati , Burhaneddin Yaman , Anton Iakovlev , Ariel Emiliano Repetur

We study overparameterization in generative adversarial networks (GANs) that can interpolate the training data. We show that overparameterization can improve generalization performance and accelerate the training process. We study the…

Machine Learning · Computer Science 2024-05-02 Lorenzo Luzi , Yehuda Dar , Richard Baraniuk