AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

User-defined Event Sampling and Uncertainty Quantification in Diffusion Models for Physical Dynamical Systems

Marc Anton Finzi, Anudhyan Boral, Andrew Gordon Wilson, Fei Sha, Leonardo Zepeda-Nunez

ICML 2023 · Image generation › Fast diffusion sampling · approach: Diffusion theory and learned samplers · 3 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 moment-matched conditional covariance in the inequality-constraint score instead of the naive constraint approximation (ablation)Conditional Diffusion · FitzHugh-Nagumotail-sample fidelityImproved
Use moment-matched conditional covariance in the inequality-constraint score instead of the naive constraint approximation (ablation)Conditional Diffusion · Lorenz attractorevent-conditional samplingImproved
Apply the probabilistic conditional score to a nonlinear inequality defining neuron spikesDiffusion model · FitzHugh-Nagumotail-sample fidelityImproved
Apply the probabilistic conditional score to a nonlinear inequality separating trajectories that do not switch attractor armsDiffusion model · Lorenz attractorevent-conditional samplingImproved
Estimate event probability using likelihood-based estimatorsDiffusion model · FitzHugh-Nagumo neuron spiking eventevent-probability calibrationHurt
Use an unconditional diffusion model to represent trajectory distributionsDiffusion model · Lorenz attractor, FitzHugh-Nagumo, and double pendulumtrajectory prediction relative errorMixed
Use the learned diffusion model to represent predictive distributionsDiffusion model · Lorenz attractoruncertainty calibrationMixed

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