Active-LATHE: An Active Learning Algorithm for Boosting the Error Exponent for Learning Homogeneous Ising Trees

DOI10.1109/TIT.2022.3222046arXiv2110.14341OpenAlexW4312390138MaRDI QIDQ6153685FDOQ6153685

Authors: Anshoo Tandon, Vincent Y. F. Tan 

Publication date: 19 March 2024

Published in: IEEE Transactions on Information Theory (Search for Journal in Brave)

Abstract: The Chow-Liu algorithm (IEEE Trans.~Inform.~Theory, 1968) has been a mainstay for the learning of tree-structured graphical models from i.i.d. sampled data vectors. Its theoretical properties have been well-studied and are well-understood. In this paper, we focus on the class of trees that are arguably even more fundamental, namely {em homogeneous} trees in which each pair of nodes that forms an edge has the same correlation $ho$. We ask whether we are able to further reduce the error probability of learning the structure of the homogeneous tree model when {em active learning} or {em active sampling of nodes or variables} is allowed. Our figure of merit is the {em error exponent}, which quantifies the exponential rate of decay of the error probability with an increasing number of data samples. At first sight, an improvement in the error exponent seems impossible, as all the edges are statistically identical. We design and analyze an algorithm Active Learning Algorithm for Trees with Homogeneous Edge (Active-LATHE), which surprisingly boosts the error exponent by at least 40% when $ho$ is at least $0.8$. For all other values of $ho$, we also observe commensurate, but more modest, improvements in the error exponent. Our analysis hinges on judiciously exploiting the minute but detectable statistical variation of the samples to allocate more data to parts of the graph in which we are less confident of being correct.

Full work available at URL: https://arxiv.org/abs/2110.14341

zbMATH Keywords

graphical modelsactive learningerror exponentsising models

Mathematics Subject Classification ID

Information and communication theory, circuits (94-XX)

This page was built for publication: Active-LATHE: An Active Learning Algorithm for Boosting the Error Exponent for Learning Homogeneous Ising Trees

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6153685)