AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Star-Shaped Denoising Diffusion Probabilistic Models

Andrey Okhotin, Dmitry Molchanov, Arkhipkin Sergeevich Vladimir, Grigory Bartosh, Viktor Ohanesian, Aibek Alanov, Dmitry P. Vetrov

NeurIPS 2023 · Image generation › Fast diffusion sampling · approach: Denoising diffusion probabilistic models

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 Dirichlet star-shaped diffusion instead of Gaussian DDPMDDPM · Dirichlet simplex dataKL: 0.200 -> 0.011Improved
use Wishart star-shaped diffusion instead of Gaussian DDPMDDPM · Wishart p.d. matricesKL: 0.096 -> 0.037Improved
use Categorical SS-DDPM instead of Multinomial Text DiffusionMTD · text8NLL (bits/char): 1.72 -> 1.69Improved
use Beta noise instead of Gaussian noiseDDPM · CIFAR-10FID: 3.17 -> 3.17No clear effect
use a Markov reverse process instead of conditioning on the whole tail (ablation)SS-DDPM · CIFAR-10 samplessample realismHurt
fewer sampling steps, Beta SS-DDPM vs DDPMBeta SS-DDPM · CIFAR-10FIDImproved
compare DDIM with SS-DDPM and DDPM at few stepsDDIM · CIFAR-10FIDMixed

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