arXiv AI July 29, 2026 By Jinhao Zhang, Zeyu Liu, Zicheng Yan, Yunquan Zhang, Guangming Tan, Fangming Liu, Daning Cheng

Mechanisms of Width Scaling in Normalized Residual Networks: The Effective Alignment Dimension

arXiv:2607. 24887v1 Announce Type: cross Abstract: Existing theories of neural-network width characterize asymptotic limits, but provide limited guidance on whether an expansion direction identified from finite training data remains beneficial on unseen data.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Machine Learning

Jun 10

Overcoming Rank Collapse in Feedback Alignment

arXiv:2606. 11123v1 Announce Type: new Abstract: Backpropagation (BP) is widely viewed as biologically implausible, in part because it requires feedback weights to be the transpose of forward weights for error propagation.

By Gauthier Boeshertz, Razvan Pascanu, Claudia Clopath

benchmarks safety

arXiv Machine Learning

Oct 9

LAIR-Net: Leaky Alignment-Impulse Residual Networks for Tabular Regression

LAIR-Net is a Leaky Alignment-Impulse Residual Network designed for tabular regression that incorporates a shallow learned anchor into each hidden state via a leaky residual transition. The authors provide a depth‑uniform bound on input‑perturbation sensitivity and show through controlled simulations that performance gains over randomized baselines stem from the anchor rather than recursion or added capacity. On 23 benchmark datasets, LAIR‑Net achieves the best average rank among eight randomized networks and twelve conventional models, with its success linked to the presence of nonlinear target structure and manageable noise levels.

By Rahul Goswami, Aryan Bhambu, Bittu Karmakar

benchmarks safety

arXiv Machine Learning

Sep 1

Branch Scaling Manifests as Implicit Architectural Regularization for Improving Generalization in Overparameterized ResNets

arXiv:2403.04545v4 Announce Type: replace Abstract: Scaling factors in residual branches have emerged as a prevalent method for boosting neural network performance, especially in normalization-free a...

By Zixiong Yu, Guhan Chen, Jianfa Lai, Bohan Li, Songtao Tian

arXiv Statistics ML

Oct 26

Early learning in large residual networks

arXiv:2610.31783v1 Announce Type: new Abstract: We study the early training dynamics of nonlinear residual networks with blocks of zero hidden layers as a model of more general residual networks. We...

By Vladimir Narovlansky, Boris Hanin

arXiv AI

Jun 8

Generalization in Deep Neural Networks: Minimax Rates for Gradient Methods

arXiv:2606. 06772v1 Announce Type: cross Abstract: Understanding the generalization performance of over-parameterized neural networks has become a central topic in deep learning theory.

By Junyu Zhou, Puyu Wang, Yunwen Lei, Marius Kloft, Yiming Ying

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

One email a morning, machine-written

Related stories

Overcoming Rank Collapse in Feedback Alignment

LAIR-Net: Leaky Alignment-Impulse Residual Networks for Tabular Regression

Branch Scaling Manifests as Implicit Architectural Regularization for Improving Generalization in Overparameterized ResNets

Early learning in large residual networks

Generalization in Deep Neural Networks: Minimax Rates for Gradient Methods

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