paper-with-me

Papers

Towards Understanding Epoch-wise Double descent in Two-layer Linear Neural Networks

2024-07-13 · Amanda Olmin, Fredrik Lindsten

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 driving this behaviour is crucial not only for understanding the generalisation behaviour of machine learning models in general, but also for employing conventional selection methods, such as the use of early stopping to mitigate overfitting. While we ultimately want to draw conclusions of more complex models, such as deep neural networks, a majority of theoretical results regarding the underlying cause of epoch-wise double descent are based on simple models, such as standard linear regression. In this paper, to take a step towards more complex models in theoretical analysis, we study epoch-wise double descent in two-layer linear neural networks. First, we derive a gradient flow for the linear two-layer model, that bridges the learning dynamics of the standard linear regression model, and the linear two-layer diagonal network with quadratic weights. Second, we identify additional factors of epoch-wise double descent emerging with the extra model layer, by deriving necessary conditions for the generalisation error to follow a double descent pattern. While epoch-wise double descent in linear regression has been attributed to differences in input variance, in the two-layer model, also the singular values of the input-output covariance matrix play an important role. This opens up for further questions regarding unidentified factors of epoch-wise double descent for truly deep models.

📄 PDF Abstract BibTeX arXiv:2407.09845

Code (0)

등록된 구현이 없습니다.

Tasks

regression

Methods 이 논문이 사용한 방법론

Linear Regression Linear Regression is a method for modelling a relationship between a dependent variable and independent variables. These models can be fit with numerous approaches. The most…
Early Stopping Early Stopping is a regularization technique for deep neural networks that stops training when parameter updates no longer begin to yield improves on a validation set. In…

Similar Papers 제목 키워드 기반

Early Stopping in Deep Networks: Double Descent and How to Eliminate it

2020-07-20 · ICLR 2021 1 · Reinhard Heckel, Fatih Furkan Yilmaz

Over-parameterized models, such as large deep networks, often exhibit a double descent phenomenon, whereas a function of model size, error first decreases, increases, and decreases at last. This intriguing double descent…

Deep Exploration of Epoch-wise Double Descent in Noisy Data: Signal Separation, Large Activation, and Benign Overfitting

2026-01-13 · Tomoki Kubo, Ryuken Uda, Yusuke Iida arxiv

Deep double descent is one of the key phenomena underlying the generalization capability of deep learning models. In this study, epoch-wise double descent, which is delayed generalization following overfitting, was empir…

When and how epochwise double descent happens

2021-08-26 · Cory Stephenson, Tyler Lee

Deep neural networks are known to exhibit a `double descent' behavior as the number of parameters increases. Recently, it has also been shown that an `epochwise double descent' effect exists in which the generalization e…

Optimization Variance: Exploring Generalization Properties of DNNs

2021-06-03 · Xiao Zhang, Dongrui Wu, Haoyi Xiong, Bo Dai

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 cur…

DiversityLearning Theory

Multi-scale Feature Learning Dynamics: Insights for Double Descent

2021-12-06 · Mohammad Pezeshki, Amartya Mitra, Yoshua Bengio, Guillaume Lajoie

A key challenge in building theoretical foundations for deep learning is the complex optimization dynamics of neural networks, resulting from the high-dimensional interactions between the large number of network paramete…