On the Complexity of the Conditional Independence Implication Problem With Bounded Cardinalities

TL;DR

This paper proves that determining whether a conditional independence implication holds for all discrete variables with bounded cardinalities is computationally very hard, specifically co-NEXPTIME-hard, even for binary variables.

Contribution

It establishes the co-NEXPTIME-hardness of the CI implication problem with bounded cardinalities, extending previous undecidability results to a bounded setting.

Findings

The problem is co-NEXPTIME-hard for all variables, including binary.

The reduction is based on a tiling problem variant.

The problem is in EXPSPACE, indicating high computational complexity.

Abstract

We show that the conditional independence (CI) implication problem with bounded cardinalities, which asks whether a given CI implication holds for all discrete random variables with given cardinalities, is co-NEXPTIME-hard. The problem remains co-NEXPTIME-hard if all variables are binary. The reduction goes from a variant of the tiling problem and is based on a prior construction used by Cheuk Ting Li to show the undecidability of a related problem where the cardinality of some variables remains unbounded. The CI implication problem with bounded cardinalities is known to be in EXPSPACE, as its negation can be stated as an existential first-order logic formula over the reals of size exponential with regard to the size of the input.