AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

Expressive power of tensor-network factorizations for probabilistic modeling

Ivan Glasser, Ryan Sweke, Nicola Pancotti, Jens Eisert, Ignacio Cirac

NeurIPS 2019 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Exact inference for probabilistic programs · 41 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use complex Born machine instead of real Born machineBorn machine · random 20x20 matrix and 8-binary-variable tensorsKL approximation error at fixed rankImproved
replace non-negative MPS with locally purified state (LPS)tensor network · random tensorsKL approximation error at fixed rank and fixed parameter countImproved
replace non-negative MPS with Born machine (BM)tensor network · UCI/biofam categorical datasets (maximum likelihood)negative log-likelihood per sample at fixed rankImproved
replace non-negative MPS with LPS (purification dimension 2)tensor network · biofam, Lymphography, SPECT Heart, Congressional Voting, Primary Tumor, Solar Flarenegative log-likelihood per sample at fixed rankImproved
compare non-negative MPS with HMM trained by Baum-WelchMPS · categorical datasetsnegative log-likelihoodNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy