Skip to content
DraconiticResearch
Search Sources API
197,761 studies31 sourcesUpdated 47 min ago
PreprintarXiv licencearXiv

Accurate Sampling from Diffusion Models

Abstract

A new proposal called DM-SMC (Diffusion Model - Sequential Monte Carlo) is investigated, which samples ensembles defined in terms of an action, using diffusion models trained on samples from the ensemble. The SMC setup allows for accurate sampling in spite of an approximate diffusion model and the finite stepsize used in the numerical solution of the stochastic process. Improved update strategies are also investigated. Results are presented for a Z2 symmetric scalar field theory in 2 dimensions near its 2nd order phase transition.

Related

  1. Accurate Molecular Size Determination by Diffusion Ordered NMR Spectroscopy Based on an Improved Diffusion Model
    Christian Urbank, Lisa Vondung
    Chemistry (Weinheim an Der Bergstrasse, Germany)Peer-reviewedCC BY 4.0Full textHigh-energy & particle physicsPMC
  2. Annealed sampling of diffusion models in lattice field theory
    Gurtej Kanwar, Octavio Vega
    arXivPreprintCC BY 4.0Full textHigh-energy & particle physicsarXiv
  3. METALICA: METAdynamics and repLICA exchange for enhanced diffusion sampling
    Alireza Omidi, Jiajun He, Jörg Gsponer +1
    arXivPreprintCC BY 4.0Full textPhysical chemistryStatisticsarXiv
  4. Thermochemically Constrained Multiscale Laplace Neural Operator to Learn Stiff Chemical Kinetics with Conditional Diffusion Model Sampling
    Dong Yang, Xiongbo Duan, Min Zhang +1
    arXivPreprintarXiv licenceFull textComputational physicsFluid dynamicsarXiv
  5. Enabling chemically accurate quantum phase estimation in the early fault-tolerant regime via unitary weight concentration
    Shota Kanasugi, Riki Toshio, Kazunori Maruyama +1
    PRX QuantumPeer-reviewedPublisher termsQuantum physics & quantum informationCrossref
BibTeX
@misc{sexty2026accurate,
  title = {{Accurate Sampling from Diffusion Models}},
  author = {Dénes Sexty},
  howpublished = {arXiv},
  year = {2026},
  month = sep,
  doi = {10.48550/arxiv.2609.29902},
  eprint = {2609.29902},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.29902},
}
RIS
TY  - UNPB
TI  - Accurate Sampling from Diffusion Models
AU  - Dénes Sexty
PY  - 2026
DA  - 2026/09/24
PB  - arXiv
DO  - 10.48550/arxiv.2609.29902
UR  - https://arxiv.org/abs/2609.29902
AB  - A new proposal called DM-SMC (Diffusion Model - Sequential Monte Carlo) is investigated, which samples ensembles defined in terms of an action, using diffusion models trained on samples from the ensemble. The SMC setup allows for accurate sampling in spite of an approximate diffusion model and the finite stepsize used in the numerical solution of the stochastic process. Improved update strategies are also investigated. Results are presented for a Z_2 symmetric scalar field theory in 2 dimensions near its 2nd order phase transition.
ER  -