Learning Abductive Reasoning Using Random Examples

Authors: Brendan Juba

AAAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We specifically consider the question of which syntactic classes of formulas have efficient algorithms for abduction. We find that the class of k-DNF explanations can be found in polynomial time for any fixed k; but, we also find evidence that even weak versions of our abduction task are intractable for the usual class of conjunctions. This evidence is provided by a connection to the usual, inductive PAC-learning model proposed by Valiant.
Researcher Affiliation Academia Brendan Juba Washington University in St. Louis bjuba@wustl.edu Work partially performed while the author was affiliated with Harvard University and supported by ONR grant number N000141210358.
Pseudocode Yes Algorithm 1: Elimination algorithm
Open Source Code No The paper does not contain any explicit statements or links indicating that source code for the described methodology is publicly available.
Open Datasets No The paper is theoretical and does not describe empirical experiments with real datasets, therefore no training dataset access information is provided.
Dataset Splits No The paper is theoretical and does not describe empirical experiments, thus no training/test/validation splits are mentioned.
Hardware Specification No The paper is theoretical and does not describe empirical experiments, thus no hardware specifications are mentioned.
Software Dependencies No The paper is theoretical and does not describe empirical experiments, thus no software dependencies with version numbers are mentioned.
Experiment Setup No The paper is theoretical and does not describe empirical experiments, thus no specific experimental setup details or hyperparameters are mentioned.