mlsanityData to 14 Oct 2026

Lessons Learned on the Path to Guaranteeing the Error Bound in Lossy Quantizers

arXiv 2407.15037 ↗First posted 21 Jul 2024cs.DCcited by 0

Not on the map. Why?

Abstract (arXiv)

Rapidly increasing data sizes in scientific computing are the driving force behind the need for lossy compression. The main drawback of lossy data compression is the introduction of error. This paper explains why many error-bounded compressors occasionally violate the error bound and presents the solutions we use in LC, a CPU/GPU compatible lossy compression framework, to guarantee the error bound for all supported types of quantizers. We show that our solutions maintain high compression ratios and cause no appreciable change in throughput.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 7 of its 19 references that are in the map. First posted on arXiv 21 Jul 2024.

Builds on

7 of 19 references.

References · 7

  1. 2021SZ3: A Modular Framework for Composing Prediction-Based Error-Bounded Lossy Compressorscited by 33
  2. 2020cuSZ: An Efficient GPU-Based Error-Bounded Lossy Compression Framework for Scientific Datacited by 18
  3. 2021SDRBench: Scientific Data Reduction Benchmark for Lossy Compressorscited by 18
  4. 2020MGARD+: Optimizing Multilevel Methods for Error-bounded Scientific Data Reductioncited by 9
  5. 2020Accelerating Multigrid-based Hierarchical Scientific Data Refactoring on GPUscited by 5
  6. 2023FZ-GPU: A Fast and High-Ratio Lossy Compressor for Scientific Computing Applications on GPUscited by 5
  7. 2021Optimizing Error-Bounded Lossy Compression for Scientific Data on GPUscited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Mitigating Artifacts in Pre-quantization Based Scientific Data Compressors with Quantization-aware Interpolation
  2. 2024A Framework for Robust Lossy Compression of Heavy-Tailed Sources
  3. 2023A Speed Odyssey for Deployable Quantization of LLMs
  4. 2026Error-bounded Point Cloud Compression Using Truncated Octahedron Quantization
  5. 2025A General Error-Theoretical Analysis Framework for Constructing Compression Strategies
  6. 2024Compression for Better: A General and Stable Lossless Compression Framework
  7. 2024Optimal Quantization for Matrix Multiplication
  8. 2024decoupleQ: Towards 2-bit Post-Training Uniform Quantization via decoupling Parameters into Integer and Floating Points