← Back to all news
arXiv Machine Learning

The Mathematical Theory of Double Descent as Shrinkage, not Overfitting: Matching Bounds for Path-Regularized Multilayer Neural Networks

The paper presents a nonasymptotic generalization theory for multilayer fully connected neural networks trained with path regularization, covering both underparameterized and overparameterized regimes without assuming bounded loss, sparsity, or width/depth limits. It explicitly models approximation error, resolves an open problem on approximation rates in generalized Barron spaces, and establishes matching upper and lower bounds that show the error curve is non‑monotone—descending, rising, then descending again—as width increases. The analysis reveals that the rise is due to shrinkage imposed by regularization rather than overfitting, and this effect cannot be eliminated by width‑independent regularization.

Related stories

arXiv AI
Sep 24

Path Regularization: A Near-Complete and Optimal Nonasymptotic Generalization Theory for Multilayer Neural Networks and Double Descent Phenomenon

The paper presents a near-complete, nonasymptotic generalization theory for multilayer neural networks using path regularization, applicable to broad Lipschitz loss functions without requiring bounded loss or extreme network hyperparameters. It provides an explicit upper bound that addresses approximation rates in generalized Barron spaces and demonstrates the double descent phenomenon for ReLU networks. The authors claim near-minimax optimality for regression problems and plan to establish matching lower bounds in future work.

By Hao Yu
efficiencysafety
More like this →
arXiv Machine Learning
Sep 23

Double Descent and Malign Overfitting in Diffusion Models

The paper investigates why diffusion models, unlike typical deep learning models, exhibit catastrophic overfitting when overparameterized. Through experiments on U‑Nets trained on CelebA and a random‑features theoretical analysis, it shows that the interpolation peak occurs at a model size proportional to the product of training samples and noise realizations, but the test loss starts to rise already at the number of samples, leading to memorization of the empirical score. Regularization techniques such as ridge penalties or early stopping can still make large models outperform smaller, unregularized ones.

By Rapha\"el Urfin, Tony Bonnaire, Giulio Biroli, Marc M\'ezard
diffusionsafety
More like this →
arXiv Machine Learning
Oct 23

Width and Depth Limits Commute During Training

arXiv:2610. 30729v1 Announce Type: new Abstract: Recent work established that the infinite-width and infinite-depth limits of residual networks commute at initialization when residual branches are scaled by $1/\sqrt{depth}$.

By Ruijia Zhang, Soufiane Hayou
More like this →
arXiv Machine Learning
Jul 30

Minimax-Optimal Generalization Bounds for Smooth Deep Neural Networks Trained by (Stochastic) Gradient Descent

arXiv:2606. 06772v2 Announce Type: replace-cross Abstract: Characterizing the optimization dynamics and statistical performance of over-parameterized deep neural networks (DNNs) remains a central challenge in understanding the remarkable success of deep learning.

By Junyu Zhou, Puyu Wang, Dennis Wagner, Yunwen Lei, Marius Kloft, Yiming Ying
More like this →