# SCRAPL: Scattering Transform with Random Paths for Machine Learning

arXiv: https://arxiv.org/abs/2602.11145 · HTML: https://mlsanity.com/paper/2602.11145/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 49 references that are in the map.
- First posted on arXiv 11 Feb 2026.

## Builds on (most cited first, 30 of 30)

- [On the Convergence of Adam and Beyond](https://mlsanity.com/paper/1904.09237/) (2019)
- [High Fidelity Neural Audio Compression](https://mlsanity.com/paper/2210.13438/) (2022)
- [PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition](https://mlsanity.com/paper/1912.10211/) (2019)
- [SAGA: A Fast Incremental Gradient Method With Support for Non-Strongly Convex Composite Objectives](https://mlsanity.com/paper/1407.0202/) (2014)
- [Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram](https://mlsanity.com/paper/1910.11480/) (2019)
- [DDSP: Differentiable Digital Signal Processing](https://mlsanity.com/paper/2001.04643/) (2020)
- [A Simple Convergence Proof of Adam and Adagrad](https://mlsanity.com/paper/2003.02395/) (2020)
- [Minimizing Finite Sums with the Stochastic Average Gradient](https://mlsanity.com/paper/1309.2388/) (2013)
- [Understanding Deep Convolutional Networks](https://mlsanity.com/paper/1601.04920/) (2016)
- [Deep Scattering Spectrum](https://mlsanity.com/paper/1304.6763/) (2013)
- [Scattering Networks for Hybrid Representation Learning](https://mlsanity.com/paper/1809.06367/) (2018)
- [A Review of Differentiable Digital Signal Processing for Music & Speech Synthesis](https://mlsanity.com/paper/2308.15422/) (2023)
- [Parametric Scattering Networks](https://mlsanity.com/paper/2107.09539/) (2021)
- [Correlation of Fr'echet Audio Distance With Human Perception of Environmental Audio Is Embedding Dependant](https://mlsanity.com/paper/2403.17508/) (2024)
- [Joint Time-Frequency Scattering](https://mlsanity.com/paper/1807.08869/) (2018)
- [Intermittent process analysis with scattering moments](https://mlsanity.com/paper/1311.4104/) (2013)
- [A Learnable ScatterNet: Locally Invariant Convolutional Layers](https://mlsanity.com/paper/1903.03137/) (2019)
- [Stochastic Approximation Beyond Gradient for Signal Processing and Machine Learning](https://mlsanity.com/paper/2302.11147/) (2023)
- [Generative networks as inverse problems with Scattering transforms](https://mlsanity.com/paper/1805.06621/) (2018)
- [Time-Frequency Scattering Accurately Models Auditory Similarities Between Instrumental Playing Techniques](https://mlsanity.com/paper/2007.10926/) (2020)
- [Generic Deep Networks with Wavelet Scattering](https://mlsanity.com/paper/1312.5940/) (2013)
- [Learning Complex Basis Functions for Invariant Representations of Audio](https://mlsanity.com/paper/1907.05982/) (2019)
- [Regularizing Neural Networks with Meta-Learning Generative Models](https://mlsanity.com/paper/2307.13899/) (2023)
- [Learning to Solve Inverse Problems for Perceptual Sound Matching](https://mlsanity.com/paper/2311.14213/) (2023)
- [Real-time Timbre Remapping with Differentiable DSP](https://mlsanity.com/paper/2407.04547/) (2024)
- [Assessing the Alignment of Audio Representations with Timbre Similarity Ratings](https://mlsanity.com/paper/2507.07764/) (2025)
- [Wavelet Scattering on the Pitch Spiral](https://mlsanity.com/paper/1601.00287/) (2016)
- [Mesostructures: Beyond Spectrogram Loss in Differentiable Time-Frequency Analysis](https://mlsanity.com/paper/2301.10183/) (2023)
- [Differentiable Time-Frequency Scattering on GPU](https://mlsanity.com/paper/2204.08269/) (2022)
- [ADAM Optimization with Adaptive Batch Selection](https://mlsanity.com/paper/2512.06795/) (2025)

## Abstract (arXiv)

The Euclidean distance between wavelet scattering transform coefficients (known as paths) provides informative gradients for perceptual quality assessment of deep inverse problems in computer vision, speech, and audio processing. However, these transforms are computationally expensive when employed as differentiable loss functions for stochastic gradient descent due to their numerous paths, which significantly limits their use in neural network training. Against this problem, we propose "Scattering transform with Random Paths for machine Learning" (SCRAPL): a stochastic optimization scheme for efficient evaluation of multivariable scattering transforms. We implement SCRAPL for the joint time-frequency scattering transform (JTFS) which demodulates spectrotemporal patterns at multiple scales and rates, allowing a fine characterization of intermittent auditory textures. We apply SCRAPL to differentiable digital signal processing (DDSP), specifically, unsupervised sound matching of a granular synthesizer and the Roland TR-808 drum machine. We also propose an initialization heuristic based on importance sampling, which adapts SCRAPL to the perceptual content of the dataset, improving neural network convergence and evaluation performance. We make our code and audio samples available and provide SCRAPL as a Python package.