用轻量级神经预测链实现高效无损压缩，速度远超现有方案。
Lossless Compression via Chained Lightweight Neural Predictors with Information Inheritance
- 构建链式轻量神经预测器，按数据统计特性动态优化参数量。
- 压缩比接近顶尖的PAC压缩器，编码速度提升1.2~6.3倍。
- 支持信息继承机制，适合追求高速压缩的部署场景。
本文研究基于神经网络的概率估计在无损数据压缩中的应用。首先，提出一种链式神经预测架构，每个单元均为参数最少的神经网络，足以高效压缩指定阶数马尔可夫源生成的数据。该架构可根据输入数据的统计特性最小化参与概率估计的总参数量。其次，引入信息继承机制，将低阶单元的概率估计结果用于高阶单元，提升压缩效率。实验表明，所提无损压缩器在链式概率估计架构下，压缩比接近当前最优的PAC压缩器；同时在消费级GPU上，编码吞吐率提升1.2至6.3倍，解码吞吐率提升2.8至12.3倍。
原文摘要 · Abstract (English)
This paper is dedicated to lossless data compression with probability estimation using neural networks. First, we propose a probability estimation architecture based on a chain of neural predictors, so that each unit of the chain is defined as a neural network with the minimum possible number of weights, which is sufficient for efficient compression of data generated by Markov sources of a given order. We show that this architecture allows us to minimize the overall number of weights participating in the probability estimation process depending on the statistical properties of the input data. Second, in order to improve compression efficiency, we introduce an information inheritance mechanism, where the probability estimate obtained by a low-order unit is used at the next higher-order unit. Experimental results show that the proposed lossless data compressor equipped with the chained probability estimation architecture provides compression ratios close to the state-of-the-art PAC compressor. At the same time, it outperforms PAC by a factor of 1.2 to 6.3 in encoding throughput and by a factor of 2.8 to 12.3 in decoding throughput on a consumer GPU.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。