# DZip: improved general-purpose lossless compression based on novel neural network modeling

arXiv: https://arxiv.org/abs/1911.03572 · HTML: https://mlsanity.com/paper/1911.03572/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Nov 2019.

## Built on by (most cited first, 6 of 6)

- [A Fast Transformer-based General-Purpose Lossless Compressor](https://mlsanity.com/paper/2203.16114/) (2022)
- [EntropyRank: Unsupervised Keyphrase Extraction via Side-Information Optimization for Language Model-based Text Compression](https://mlsanity.com/paper/2308.13399/) (2023)
- [An Efficient Compression of Deep Neural Network Checkpoints Based on Prediction and Context Modeling](https://mlsanity.com/paper/2506.12000/) (2025)
- [In-Context Source and Channel Coding](https://mlsanity.com/paper/2601.10267/) (2026)
- [Lossless Compression: A New Benchmark for Time Series Model Evaluation](https://mlsanity.com/paper/2509.21002/) (2025)
- [Lossless Compression via Chained Lightweight Neural Predictors with Information Inheritance](https://mlsanity.com/paper/2604.15472/) (2026)

## Abstract (arXiv)

We consider lossless compression based on statistical data modeling followed by prediction-based encoding, where an accurate statistical model for the input data leads to substantial improvements in compression. We propose DZip, a general-purpose compressor for sequential data that exploits the well-known modeling capabilities of neural networks (NNs) for prediction, followed by arithmetic coding. Dzip uses a novel hybrid architecture based on adaptive and semi-adaptive training. Unlike most NN based compressors, DZip does not require additional training data and is not restricted to specific data types, only needing the alphabet size of the input data. The proposed compressor outperforms general-purpose compressors such as Gzip (on average 26% reduction) on a variety of real datasets, achieves near-optimal compression on synthetic datasets, and performs close to specialized compressors for large sequence lengths, without any human input. The main limitation of DZip in its current implementation is the encoding/decoding time, which limits its practicality. Nevertheless, the results showcase the potential of developing improved general-purpose compressors based on neural networks and hybrid modeling.