English
Related papers

Related papers: Regularization-wise double descent: Why it occurs …

200 papers

Double descent refers to the phase transition that is exhibited by the generalization error of unregularized learning models when varying the ratio between the number of parameters and the number of training samples. The recent success of…

Machine Learning · Computer Science 2020-06-19 Michał Dereziński , Feynman Liang , Michael W. Mahoney

The appearance of the double-descent risk phenomenon has received growing interest in the machine learning and statistics community, as it challenges well-understood notions behind the U-shaped train-test curves. Motivated through…

Machine Learning · Statistics 2020-11-11 Prasad Cheema , Mahito Sugiyama

Neural networks are more expressive when they have multiple layers. In turn, conventional training methods are only successful if the depth does not lead to numerical issues such as exploding or vanishing gradients, which occur less…

Machine Learning · Computer Science 2022-06-07 Carles Riera , Camilo Rey , Thiago Serra , Eloi Puertas , Oriol Pujol

In this paper, we provide a precise characterization of generalization properties of high dimensional kernel ridge regression across the under- and over-parameterized regimes, depending on whether the number of training data n exceeds the…

Machine Learning · Statistics 2021-02-25 Fanghui Liu , Zhenyu Liao , Johan A. K. Suykens

The double descent (DD) paradox, where over-parameterized models see generalization improve past the interpolation point, remains largely unexplored in the non-stationary domain of Deep Reinforcement Learning (DRL). We present preliminary…

Machine Learning · Computer Science 2025-11-11 Viktor Veselý , Aleksandar Todorov , Matthia Sabatelli

This study demonstrates that double descent can be mitigated by adding a dropout layer adjacent to the fully connected linear layer. The unexpected double-descent phenomenon garnered substantial attention in recent years, resulting in…

Machine Learning · Computer Science 2025-08-08 Tian-Le Yang , Joe Suzuki

Classical statistical learning theory predicts a U-shaped relationship between test loss and model capacity, driven by the bias-variance trade-off. Recent advances in modern machine learning have revealed a more complex pattern,…

Machine Learning · Statistics 2026-04-23 Yin Liu , Jianwen Cai , Didong Li

Regularization plays an important role in generalization of deep neural networks, which are often prone to overfitting with their numerous parameters. L1 and L2 regularizers are common regularization tools in machine learning with their…

Machine Learning · Computer Science 2019-10-21 Dae Hoon Park , Chiu Man Ho , Yi Chang , Huaqing Zhang

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

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

Recently, over-parameterized neural networks have been extensively analyzed in the literature. However, the previous studies cannot satisfactorily explain why fully trained neural networks are successful in practice. In this paper, we…

Machine Learning · Computer Science 2019-10-28 Cong Fang , Hanze Dong , Tong Zhang

Various classical machine learning models, including linear regression, kernel methods, and deep neural networks, exhibit double descent, in which the test risk peaks near the interpolation threshold and then decreases in the…

Quantum Physics · Physics 2026-04-21 Kensuke Kamisoyama , Lento Nagano , Koji Terashi

It has been observed by Belkin et al.\ that over-parametrized neural networks exhibit a `double descent' phenomenon. That is, as the model complexity (as reflected in the number of features) increases, the test error initially decreases,…

Optimization and Control · Mathematics 2025-09-16 Vivek Shripad Borkar

Neural growth is the process of growing a small neural network to a large network and has been utilized to accelerate the training of deep neural networks. One crucial aspect of neural growth is determining the optimal growth timing.…

Machine Learning · Computer Science 2024-01-09 Haihang Wu , Wei Wang , Tamasha Malepathirana , Damith Senanayake , Denny Oetomo , Saman Halgamuge

We explore the low-rank structure of the weight matrices in neural networks at the stationary points (limiting solutions of optimization algorithms) with $L2$ regularization (also known as weight decay). We show several properties of such…

Machine Learning · Computer Science 2025-08-21 Ilja Kuzborskij , Yasin Abbasi Yadkori

Deep learning methods operate in regimes that defy the traditional statistical mindset. Neural network architectures often contain more parameters than training samples, and are so rich that they can interpolate the observed labels, even if…

Statistics Theory · Mathematics 2020-12-14 Song Mei , Andrea Montanari

The role of $L^2$ regularization, in the specific case of deep neural networks rather than more traditional machine learning models, is still not fully elucidated. We hypothesize that this complex interplay is due to the combination of…

Machine Learning · Computer Science 2019-02-11 Pierre H. Richemond , Yike Guo

Classical learning theory suggests that the optimal generalization performance of a machine learning model should occur at an intermediate model complexity, with simpler models exhibiting high bias and more complex models exhibiting high…

Machine Learning · Statistics 2020-11-09 Ben Adlam , Jeffrey Pennington

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

Modern machine learning models often employ a huge number of parameters and are typically optimized to have zero training loss; yet surprisingly, they possess near-optimal prediction performance, contradicting classical learning theory. We…

Machine Learning · Statistics 2021-06-08 Zhu Li , Zhi-Hua Zhou , Arthur Gretton