# Deep Network Classification by Scattering and Homotopy Dictionary Learning

arXiv: https://arxiv.org/abs/1910.03561 · HTML: https://mlsanity.com/paper/1910.03561/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Oct 2019.

## Built on by (most cited first, 17 of 17)

- [Learning to Optimize: A Primer and A Benchmark](https://mlsanity.com/paper/2103.12828/) (2021)
- [Efficient and Modular Implicit Differentiation](https://mlsanity.com/paper/2105.15183/) (2021)
- [White-Box Transformers via Sparse Rate Reduction](https://mlsanity.com/paper/2306.01129/) (2023)
- [Understanding approximate and unrolled dictionary learning for pattern recovery](https://mlsanity.com/paper/2106.06338/) (2021)
- [Scaling White-Box Transformers for Vision](https://mlsanity.com/paper/2405.20299/) (2024)
- [The Unreasonable Effectiveness of Patches in Deep Convolutional Kernels Methods](https://mlsanity.com/paper/2101.07528/) (2021)
- [Phase Collapse in Neural Networks](https://mlsanity.com/paper/2110.05283/) (2021)
- [Decision boundaries and convex hulls in the feature space that deep learning functions learn from images](https://mlsanity.com/paper/2202.04052/) (2022)
- [Resource-Efficient Invariant Networks: Exponential Gains by Unrolled Optimization](https://mlsanity.com/paper/2203.05006/) (2022)
- [On the Shift Invariance of Max Pooling Feature Maps in Convolutional Neural Networks](https://mlsanity.com/paper/2209.11740/) (2022)
- [Efficient Hybrid Network: Inducting Scattering Features](https://mlsanity.com/paper/2203.15392/) (2022)
- [The Maximal Overlap Discrete Wavelet Scattering Transform and Its Application in Classification Tasks](https://mlsanity.com/paper/2506.12039/) (2025)
- [Learned Interpretable Residual Extragradient ISTA for Sparse Coding](https://mlsanity.com/paper/2106.11970/) (2021)
- [Cascaded Compressed Sensing Networks: A Reversible Architecture for Layerwise Learning](https://mlsanity.com/paper/2110.10379/) (2021)
- [Ternary and Binary Quantization for Improved Classification](https://mlsanity.com/paper/2203.16798/) (2022)
- [From CNNs to Shift-Invariant Twin Models Based on Complex Wavelets](https://mlsanity.com/paper/2212.00394/) (2022)
- [Denoising: from classical methods to deep CNNs](https://mlsanity.com/paper/2404.16617/) (2024)

## Abstract (arXiv)

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 ℓ1 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.