English
Related papers

Related papers: Manipulating Sparse Double Descent

200 papers

Neural networks are usually not the tool of choice for nonparametric high-dimensional problems where the number of input features is much larger than the number of observations. Though neural networks can approximate complex multivariate…

Methodology · Statistics 2019-06-25 Jean Feng , Noah Simon

It has been shown that gradient descent can yield the zero training loss in the over-parametrized regime (the width of the neural networks is much larger than the number of data points). In this work, combining the ideas of some existing…

Optimization and Control · Mathematics 2019-11-05 Lei Li

In unsupervised learning, dimensionality reduction is an important tool for data exploration and visualization. Because these aims are typically open-ended, it can be useful to frame the problem as looking for patterns that are enriched in…

Machine Learning · Statistics 2018-11-16 Kristen Severson , Soumya Ghosh , Kenney Ng

Training deep neural networks with an $L_0$ regularization is one of the prominent approaches for network pruning or sparsification. The method prunes the network during training by encouraging weights to become exactly zero. However,…

Machine Learning · Computer Science 2021-07-02 Yang Li , Shihao Ji

Mechanistic interpretability aims to understand how neural networks generalize beyond their training data by reverse-engineering their internal structures. We introduce patterning as the dual problem: given a desired form of generalization,…

Machine Learning · Computer Science 2026-01-21 George Wang , Daniel Murfet

We study the loss surface of DNNs with $L_{2}$ regularization. We show that the loss in terms of the parameters can be reformulated into a loss in terms of the layerwise activations $Z_{\ell}$ of the training set. This reformulation reveals…

Machine Learning · Statistics 2022-10-17 Arthur Jacot , Eugene Golikov , Clément Hongler , Franck Gabriel

We study the emergence of sparse representations in neural networks. We show that in unsupervised models with regularization, the emergence of sparsity is the result of the input data samples being distributed along highly non-linear or…

Machine Learning · Computer Science 2019-03-08 Vivek Bakaraju , Kishore Reddy Konda

Model sparsification in deep learning promotes simpler, more interpretable models with fewer parameters. This not only reduces the model's memory footprint and computational needs but also shortens inference time. This work focuses on…

Computer Vision and Pattern Recognition · Computer Science 2023-12-01 Richa Upadhyay , Ronald Phlypo , Rajkumar Saini , Marcus Liwicki

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 empirically investigated…

Machine Learning · Computer Science 2026-01-14 Tomoki Kubo , Ryuken Uda , Yusuke Iida

Most of the recent successful applications of neural networks have been based on training with gradient descent updates. However, for some small networks, other mirror descent updates learn provably more efficiently when the target is…

Machine Learning · Computer Science 2020-06-24 Ehsan Amid , Manfred K. Warmuth

This paper explores the generalization loss of linear regression in variably parameterized families of models, both under-parameterized and over-parameterized. We show that the generalization curve can have an arbitrary number of peaks, and…

Machine Learning · Computer Science 2021-11-09 Lin Chen , Yifei Min , Mikhail Belkin , Amin Karbasi

Generalization to unseen degradations remains a fundamental challenge for low-level vision models. This paper aims to investigate the underlying mechanism of this failure, using image deraining as a primary case study due to its…

Computer Vision and Pattern Recognition · Computer Science 2026-02-25 Jinfan Hu , Zhiyuan You , Jinjin Gu , Kaiwen Zhu , Tianfan Xue , Chao Dong

We showcase important features of the dynamics of the Stochastic Gradient Descent (SGD) in the training of neural networks. We present empirical observations that commonly used large step sizes (i) lead the iterates to jump from one side of…

Machine Learning · Computer Science 2023-06-08 Maksym Andriushchenko , Aditya Varre , Loucas Pillaud-Vivien , Nicolas Flammarion

Sparse signal recovery problems from noisy linear measurements appear in many areas of wireless communications. In recent years, deep learning (DL) based approaches have attracted interests of researchers to solve the sparse linear inverse…

Signal Processing · Electrical Eng. & Systems 2021-01-28 Wei Chen , Bowen Zhang , Shi Jin , Bo Ai , Zhangdui Zhong

Recent studies have uncovered intriguing phenomena in deep learning, such as grokking, double descent, and emergent abilities in large language models, which challenge human intuition and are crucial for a deeper understanding of neural…

Machine Learning · Computer Science 2024-02-27 Yufei Huang , Shengding Hu , Xu Han , Zhiyuan Liu , Maosong Sun

In this study, the problem of computing a sparse representation of multi-dimensional visual data is considered. In general, such data e.g., hyperspectral images, color images or video data consists of signals that exhibit strong local…

Computer Vision and Pattern Recognition · Computer Science 2023-03-16 Alexandros Gkillas , Dimitris Ampeliotis , Kostas Berberidis

When an online learning algorithm is used to estimate the unknown parameters of a model, the signals interacting with the parameter estimates should not decay too quickly for the optimal values to be discovered correctly. This requirement…

Machine Learning · Computer Science 2019-11-05 Kamil Nar , S. Shankar Sastry

This paper investigates the predictive performance of model averaging in high-dimensional linear regression where the number of regressors is comparable to the sample size. We demonstrate that the double descent trajectory manifests within…

Methodology · Statistics 2026-05-14 Ke Chen , Dandan Jiang , Xinyu Zhang

Dropout is a regularization technique widely used in training artificial neural networks to mitigate overfitting. It consists of dynamically deactivating subsets of the network during training to promote more robust representations. Despite…

Machine Learning · Statistics 2025-09-10 Francesco Mori , Francesca Mignacco

Machine learning methods are commonly used to solve inverse problems, wherein an unknown signal must be estimated from few indirect measurements generated via a known acquisition procedure. In particular, neural networks perform well…

Machine Learning · Computer Science 2025-12-05 Hannah Laus , Suzanna Parkinson , Vasileios Charisopoulos , Felix Krahmer , Rebecca Willett