Sampling first order logical particles

Hannaneh Hajishirzi, Eyal Amir
Proceedings of the 24th Conference on Uncertainty in Artificial Intelligence, PMLR R6:248-255, 2008.

Abstract

Approximate inference in dynamic systems is the problem of estimating the state of the system given a sequence of actions and partial observations. High precision estimation is fundamental in many applications like diagnosis, natural language processing, tracking, planning, and robotics. In this paper we present an algorithm that samples possible deterministic executions of a probabilistic sequence. The algorithm takes advantage of a compact representation (using first order logic) for actions and world states to improve the precision of its estimation. Theoretical and empirical results show that the algorithm’s expected error is smaller than propositional sampling and Sequential Monte Carlo (SMC) sampling techniques.

Cite this Paper

BibTeX
@InProceedings{pmlr-vR6-hajishirzi08a, title = {Sampling first order logical particles}, author = {Hajishirzi, Hannaneh and Amir, Eyal}, booktitle = {Proceedings of the 24th Conference on Uncertainty in Artificial Intelligence}, pages = {248--255}, year = {2008}, editor = {McAllester, David A. and Myllymäki, Petri}, volume = {R6}, series = {Proceedings of Machine Learning Research}, month = {09--12 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/r6/main/assets/hajishirzi08a/hajishirzi08a.pdf}, url = {https://proceedings.mlr.press/r6/hajishirzi08a.html}, abstract = {Approximate inference in dynamic systems is the problem of estimating the state of the system given a sequence of actions and partial observations. High precision estimation is fundamental in many applications like diagnosis, natural language processing, tracking, planning, and robotics. In this paper we present an algorithm that samples possible deterministic executions of a probabilistic sequence. The algorithm takes advantage of a compact representation (using first order logic) for actions and world states to improve the precision of its estimation. Theoretical and empirical results show that the algorithm’s expected error is smaller than propositional sampling and Sequential Monte Carlo (SMC) sampling techniques.}, note = {Reissued by PMLR on 09 October 2024.} }
Endnote
%0 Conference Paper %T Sampling first order logical particles %A Hannaneh Hajishirzi %A Eyal Amir %B Proceedings of the 24th Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2008 %E David A. McAllester %E Petri Myllymäki %F pmlr-vR6-hajishirzi08a %I PMLR %P 248--255 %U https://proceedings.mlr.press/r6/hajishirzi08a.html %V R6 %X Approximate inference in dynamic systems is the problem of estimating the state of the system given a sequence of actions and partial observations. High precision estimation is fundamental in many applications like diagnosis, natural language processing, tracking, planning, and robotics. In this paper we present an algorithm that samples possible deterministic executions of a probabilistic sequence. The algorithm takes advantage of a compact representation (using first order logic) for actions and world states to improve the precision of its estimation. Theoretical and empirical results show that the algorithm’s expected error is smaller than propositional sampling and Sequential Monte Carlo (SMC) sampling techniques. %Z Reissued by PMLR on 09 October 2024.
APA
Hajishirzi, H. & Amir, E.. (2008). Sampling first order logical particles. Proceedings of the 24th Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research R6:248-255 Available from https://proceedings.mlr.press/r6/hajishirzi08a.html. Reissued by PMLR on 09 October 2024.

Related Material