iVPF: Numerical Invertible Volume Preserving Flow for Efficient Lossless Compression
This addresses the problem of high-performance lossless compression for data storage, offering a novel method that improves efficiency over lightweight algorithms, though it appears incremental in the context of flow-based models.
The paper tackles the challenge of efficient lossless compression for big data by proposing iVPF, a numerical invertible volume preserving flow that enables exact bijective mapping without errors, achieving state-of-the-art compression ratios on various datasets.
It is nontrivial to store rapidly growing big data nowadays, which demands high-performance lossless compression techniques. Likelihood-based generative models have witnessed their success on lossless compression, where flow based models are desirable in allowing exact data likelihood optimisation with bijective mappings. However, common continuous flows are in contradiction with the discreteness of coding schemes, which requires either 1) imposing strict constraints on flow models that degrades the performance or 2) coding numerous bijective mapping errors which reduces the efficiency. In this paper, we investigate volume preserving flows for lossless compression and show that a bijective mapping without error is possible. We propose Numerical Invertible Volume Preserving Flow (iVPF) which is derived from the general volume preserving flows. By introducing novel computation algorithms on flow models, an exact bijective mapping is achieved without any numerical error. We also propose a lossless compression algorithm based on iVPF. Experiments on various datasets show that the algorithm based on iVPF achieves state-of-the-art compression ratio over lightweight compression algorithms.