arXiv AI June 30, 2026 By Yi-Shan Chu

S-GAI: Spectral Geometry-Aware Initialization for Sigmoidal MLPs -- From Dataset Geometry to Network Weights

arXiv:2606. 28444v1 Announce Type: cross Abstract: Classical universal approximation theorems establish the expressive power of sigmoidal multilayer perceptrons, but they do not prescribe how initial weights should encode the geometry of a data distribution.

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 AI

3d ago

From Dataset Spectral Geometry to Network Weights: A Geometry-Aware Initialization for Sigmoidal MLPs in Image Classification

arXiv:2606.28444v2 Announce Type: replace-cross Abstract: Classical universal approximation theorems (UAT) establish the expressive power of sigmoidal multilayer perceptrons, but they do not specify...

By Yi-Shan Chu

computer-vision

Hugging Face Trending Papers

Jun 24

Pre-Warm: Input-Conditioned Weight Initialization for Convolutional Neural Networks

We introduce Pre-Warm, a simple yet effective zero-training-cost method for data-conditioned initialization of the first convolutional layer. Before the first forward pass, Pre-Warm extracts mean-centered local patches from a single training batch, clusters them with MiniBatchKMeans, applies inverse Manhattan spatial weighting, and uses the resulting centroids to initialize half of the first-layer filters (the remainder retain Kaiming initialization).

benchmarks

arXiv Machine Learning

Jun 25

Pre-Warm: Input-Conditioned Weight Initialization for Convolutional Neural Networks

arXiv:2606. 25256v1 Announce Type: cross Abstract: We introduce Pre-Warm, a simple yet effective zero-training-cost method for data-conditioned initialization of the first convolutional layer.

By Rowan Martnishn

benchmarks

arXiv AI

Sep 18

Green-ELM: Efficient Analytic Learning via High-Dimensional Random Projections

arXiv:2604. 15613v4 Announce Type: replace-cross Abstract: We present Green-ELM, a non-iterative neural architecture that replaces gradient-based optimization of the output layer with a closed-form analytic solution over a fixed, high-dimensional random feature representation.

By Wladimir Silva

arXiv Machine Learning

Jun 4

HalfNet: Randomized Neural Networks with Learned Subspace Geometry

arXiv:2606. 04583v1 Announce Type: new Abstract: Many researchers investigated neural networks with some of their weights fixed to values randomly drawn from a given distribution, e.

By Ethem Alpaydin

rag

Hugging Face Trending Papers

Jun 22

Sublinearly Structured Deep Neural Networks Achieve Feature Learning Consistency for Compositional Functions

Over the past decade, deep neural networks (DNNs) have achieved remarkable success on complex machine-learning tasks, yet the theoretical foundations of their performance remain incomplete. From a statistical viewpoint, a natural question is: can DNNs attain feature-learning and prediction consistency comparable to that of classical models?

computer-vision benchmarks

One email a morning, machine-written

Related stories

From Dataset Spectral Geometry to Network Weights: A Geometry-Aware Initialization for Sigmoidal MLPs in Image Classification

Pre-Warm: Input-Conditioned Weight Initialization for Convolutional Neural Networks

Pre-Warm: Input-Conditioned Weight Initialization for Convolutional Neural Networks

Green-ELM: Efficient Analytic Learning via High-Dimensional Random Projections

HalfNet: Randomized Neural Networks with Learned Subspace Geometry

Sublinearly Structured Deep Neural Networks Achieve Feature Learning Consistency for Compositional Functions