Bayesian Tensor Network with Polynomial Complexity for Probabilistic Machine Learning
From MaRDI portal
Publication:6332005
arXiv1912.12923MaRDI QIDQ6332005
Author name not available (Why is that?)
Publication date: 30 December 2019
Abstract: It is known that describing or calculating the conditional probabilities of multiple events is exponentially expensive. In this work, Bayesian tensor network (BTN) is proposed to efficiently capture the conditional probabilities of multiple sets of events with polynomial complexity. BTN is a directed acyclic graphical model that forms a subset of TN. To testify its validity for exponentially many events, BTN is implemented to the image recognition, where the classification is mapped to capturing the conditional probabilities in an exponentially large sample space. Competitive performance is achieved by the BTN with simple tree network structures. Analogous to the tensor network simulations of quantum systems, the validity of the simple-tree BTN implies an ``area law of fluctuations in image recognition problems.
Has companion code repository: https://github.com/ranshiju/BayesianTN
This page was built for publication: Bayesian Tensor Network with Polynomial Complexity for Probabilistic Machine Learning
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6332005)
