Pith. sign in

REVIEW 1 cited by

Discrete generative diffusion models without stochastic differential equations: a tensor network approach

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2407.11133 v1 pith:ILTS4MQC submitted 2024-07-15 cond-mat.stat-mech cond-mat.dis-nncs.LG

classification cond-mat.stat-mechcond-mat.dis-nncs.LG
keywords modelsdifferentialdiffusiondiscretedistributionlearningstochasticwithout
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

Diffusion models (DMs) are a class of generative machine learning methods that sample a target distribution by transforming samples of a trivial (often Gaussian) distribution using a learned stochastic differential equation. In standard DMs, this is done by learning a ``score function'' that reverses the effect of adding diffusive noise to the distribution of interest. Here we consider the generalisation of DMs to lattice systems with discrete degrees of freedom, and where noise is added via Markov chain jump dynamics. We show how to use tensor networks (TNs) to efficiently define and sample such ``discrete diffusion models'' (DDMs) without explicitly having to solve a stochastic differential equation. We show the following: (i) by parametrising the data and evolution operators as TNs, the denoising dynamics can be represented exactly; (ii) the auto-regressive nature of TNs allows to generate samples efficiently and without bias; (iii) for sampling Boltzmann-like distributions, TNs allow to construct an efficient learning scheme that integrates well with Monte Carlo. We illustrate this approach to study the equilibrium of two models with non-trivial thermodynamics, the $d=1$ constrained Fredkin chain and the $d=2$ Ising model.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Effective dimensional reduction of complex systems based on tensor networks

    cond-mat.stat-mech 2024-11 conditional novelty 6.0 of 10

    Matrix Product State approximations of the network epidemic steady state can be tuned by bond dimension and outperform second-order mean-field theory for sufficiently large bond dimensions.

Pith tools