High-Dimensional Dataset Entropy Estimation via Lossy Compression

Ivan D. Butakov, Sofia Malanchuk, A. M. Neopryatnaya, A. D. Tolmachev, Kirill Andreev, Stanislav Kruglik, Evgeny Marshakov, Alexey Frolov · Journal of Communications Technology and Electronics · 2021

Abstract This paper proposes a method for estimating a high-dimensional dataset entropy based on compression via autoencoder. We give theoretical proof of such estimation relevance and illustrate it by experiments with synthetic data and the MNIST digits dataset.

Read the paper · More papers on PaperTik