(2022) Formally Justifying MDL-based Inference of Cause and Effect.
|
Text
amcmdl-marx,vreeken.pdf Download (127kB) | Preview |
Abstract
The algorithmic independence of conditionals, which postu- lates that the causal mechanism is algorithmically indepen- dent of the cause, has recently inspired many highly success- ful approaches to distinguish cause from effect given only observational data. Most popular among these is the idea to approximate algorithmic independence via two-part Mini- mum Description Length (MDL). Although intuitively sen- sible, the link between the original postulate and practical two-part MDL encodings has so far been left vague. In this work, we close this gap by deriving a two-part formulation of this postulate, in terms of Kolmogorov complexity, which directly links to practical MDL encodings. To close the cy- cle, we prove that this formulation leads on expectation to the same inference result as the original postulate.
| Item Type: | Conference or Workshop Item (A Paper) (Paper) |
|---|---|
| Divisions: | Jilles Vreeken (Exploratory Data Analysis) |
| Conference: | AAAI National Conference of the American Association for Artificial Intelligence |
| Depositing User: | Sebastian Dalleiger |
| Date Deposited: | 15 Jul 2022 10:11 |
| Last Modified: | 15 Jul 2022 10:11 |
| Primary Research Area: | NRA1: Trustworthy Information Processing |
| URI: | https://publications.cispa.saarland/id/eprint/3730 |
Actions
Actions (login required)
 |
View Item |