# Deep Network Classification by Scattering and Homotopy Dictionary Learning

Source: [Deep Network Classification by Scattering and Homotopy Dictionary Learning](<https://www.sota2.com/research/paper/68fa671c1e209131cea14549>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T22:06:19.934Z

Authors: John Zarka, Louis Thiry, Tom\\'as Angles, St\\'ephane Mallat

Published: 2019-10-08T17:47:44.000Z

## Abstract

We introduce a sparse scattering deep convolutional neural network, which provides a simple model to analyze properties of deep representation learning for classification. Learning a single dictionary matrix with a classifier yields a higher classification accuracy than AlexNet over the ImageNet 2012 dataset. The network first applies a scattering transform that linearizes variabilities due to geometric transformations such as translations and small deformations. A sparse $\\ell^1$ dictionary coding reduces intra-class variability while preserving class separation through projections over unions of linear spaces. It is implemented in a deep convolutional network with a homotopy algorithm having an exponential convergence. A convergence proof is given in a general framework that includes ALISTA. Classification results are analyzed on ImageNet.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1910.03561>)

[PDF](<https://arxiv.org/pdf/1910.03561.pdf>)