mlsanityData to 7 Oct 2026

Sparse L1-Autoencoders for Scientific Data Compression

arXiv 2405.14270 ↗First posted 23 May 2024cs.LG cs.AI cs.NAcited by 4

Not on the map. Why?

Abstract (arXiv)

Scientific datasets present unique challenges for machine learning-driven compression methods, including more stringent requirements on accuracy and mitigation of potential invalidating artifacts. Drawing on results from compressed sensing and rate-distortion theory, we introduce effective data compression methods by developing autoencoders using high dimensional latent spaces that are L1-regularized to obtain sparse low dimensional representations. We show how these information-rich latent spaces can be used to mitigate blurring and other artifacts to obtain highly effective data compression methods for scientific data. We demonstrate our methods for short angle scattering (SAS) datasets showing they can achieve compression ratios around two orders of magnitude and in some cases better. Our compression methods show promise for use in addressing current bottlenecks in transmission, storage, and analysis in high-performance distributed computing environments. This is central to processing the large volume of SAS data being generated at shared experimental facilities around the world to support scientific investigations. Our approaches provide general ways for obtaining specialized compression methods for targeted scientific datasets.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 15 of its 51 references that are in the map. First posted on arXiv 23 May 2024.

Builds on

15 of 51 references.

References · 15

  1. 2017Learning Sparse Neural Networks through L0 Regularizationcited by 571
  2. 2023High-Fidelity Audio Compression with Improved RVQGANcited by 423
  3. 2017Lossy Image Compression with Compressive Autoencoderscited by 289
  4. 2018Model compression via distillation and quantizationcited by 287
  5. 2019Physics-Constrained Deep Learning for High-dimensional Surrogate Modeling and Uncertainty Quantification without Labeled Datacited by 261
  6. 2013k-Sparse Autoencoderscited by 209
  7. 2016Group Sparse Regularization for Deep Neural Networkscited by 89
  8. 2018Deep Convolutional AutoEncoder-based Lossy Image Compressioncited by 42
  9. 2018From Principal Subspaces to Principal Components with Linear Autoencoderscited by 38
  10. 2018Relational Autoencoder for Feature Extractioncited by 23
  11. 2024A Comprehensive Review of Latent Space Dynamics Identification Algorithms for Intrusive and Non-Intrusive Reduced-Order-Modelingcited by 22
  12. 2021Exploring Autoencoder-based Error-bounded Compression for Scientific Datacited by 19
3 more
  1. 2023Bi-fidelity Variational Auto-encoder for Uncertainty Quantificationcited by 8
  2. 2023Are We Using Autoencoders in a Wrong Way?cited by 2
  3. 2023Goal-oriented Uncertainty Quantification for Inverse Problems via Variational Encoder-Decoder Networkscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 2.

4 papers.

  1. 2025Good Things Come in Pairs: Paired Autoencoders for Inverse Problemscited by 5
  2. 2025Improving Cardiac Risk Prediction Using Data Generation Techniquescited by 0
  3. 2026Variational Sparse Paired Autoencoders (vsPAIR) for Inverse Problems and Uncertainty Quantificationcited by 0
  4. 2026Physics-conforming Latent Twinscited by 0