Proposes a causal discovery method for bivariate systems combining rate-distortion theory with minimum description length (MDL) and information-theoretic dimension analysis. Addresses fundamental challenges in inferring causal direction from observational data using information-theoretic foundations.
Research
Bivariate Causal Discovery Using Rate-Distortion MDL: An Information Dimension Approach
Researchers combine rate-distortion theory with MDL (minimum description length) to solve bivariate causal discovery from observational data—determining which variable causes which using information-theoretic dimension analysis.
Wednesday, April 8, 2026 12:00 PM UTC2 MIN READSOURCE: arXiv CS.LG (Machine Learning)BY sys://pipeline
Tags
research