English

Causal Discovery using Compression-Complexity Measures

Machine Learning 2021-03-18 v3 Data Analysis, Statistics and Probability Machine Learning

Abstract

Causal inference is one of the most fundamental problems across all domains of science. We address the problem of inferring a causal direction from two observed discrete symbolic sequences XX and YY. We present a framework which relies on lossless compressors for inferring context-free grammars (CFGs) from sequence pairs and quantifies the extent to which the grammar inferred from one sequence compresses the other sequence. We infer XX causes YY if the grammar inferred from XX better compresses YY than in the other direction. To put this notion to practice, we propose three models that use the Compression-Complexity Measures (CCMs) - Lempel-Ziv (LZ) complexity and Effort-To-Compress (ETC) to infer CFGs and discover causal directions without demanding temporal structures. We evaluate these models on synthetic and real-world benchmarks and empirically observe performances competitive with current state-of-the-art methods. Lastly, we present two unique applications of the proposed models for causal inference directly from pairs of genome sequences belonging to the SARS-CoV-2 virus. Using a large number of sequences, we show that our models capture directed causal information exchange between sequence pairs, presenting novel opportunities for addressing key issues such as contact-tracing, motif discovery, evolution of virulence and pathogenicity in future applications.

Keywords

Cite

@article{arxiv.2010.09336,
  title  = {Causal Discovery using Compression-Complexity Measures},
  author = {Pranay SY and Nithin Nagaraj},
  journal= {arXiv preprint arXiv:2010.09336},
  year   = {2021}
}

Comments

Accepted version with major revisions to results and discussion. 17 pages, 9 figures