Lossless Compression via Chained Lightweight Neural Predictors with Information Inheritance

ArXi:2604.15472v1 Announce Type: cross 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 Marko sources of a given order.