Dynamic Importance Sampling for Anytime Bounds of the Partition Function

Authors: Qi Lou, Rina Dechter, Alexander T. Ihler

NeurIPS 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We demonstrate the effectiveness of our approach empirically on real-world problem instances taken from recent UAI competitions.
Researcher Affiliation Academia Qi Lou Computer Science Univ. of California, Irvine Irvine, CA 92697, USA qlou@ics.uci.edu Rina Dechter Computer Science Univ. of California, Irvine Irvine, CA 92697, USA dechter@ics.uci.edu Alexander Ihler Computer Science Univ. of California, Irvine Irvine, CA 92697, USA ihler@ics.uci.edu
Pseudocode Yes Algorithm 1 Dynamic importance sampling (DIS)
Open Source Code No The paper does not provide an explicit statement or link for open-source code for the described methodology.
Open Datasets Yes Our benchmarks include pedigree, 22 genetic linkage instances from the UAI 08 inference challenge1; protein, 50 randomly selected instances made from the small protein side-chains of [22]; and BN, 50 randomly selected Bayesian networks from the UAI 06 competition2. 1http://graphmod.ics.uci.edu/uai08/Evaluation/Report/Benchmarks/ 2http://melodi.ee.washington.edu/~bilmes/uai06Inference Evaluation/
Dataset Splits No The paper mentions evaluating on 'real-world problem instances from recent UAI competitions' and different benchmarks, but it does not specify explicit training, validation, or test dataset splits used for their experiments.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory, or cloud resources) used for running the experiments.
Software Dependencies No The paper states 'All implementations are in C/C++', but does not list specific software dependencies with version numbers (e.g., libraries, frameworks, or solvers).
Experiment Setup Yes We alloted 1GB memory to all methods, first computing the largest ibound that fits the memory budget, and using the remaining memory for search. ... We show DIS for two settings, (Nl=1, Nd=1) and (Nl=1, Nd=10), balancing the effort between search and sampling. ... We set δ = 0.025 and ran each algorithm for 1 hour.