AI Paper Atlas

Research map / Probabilistic and scientific modeling / Differential equations and PDEs

Scalable Inference in SDEs by Direct Matching of the Fokker–Planck–Kolmogorov Equation

Arno Solin, Ella Maija Tamir, Prakhar Verma

NeurIPS 2021 · Probabilistic and scientific modeling › Differential equations and PDEs · approach: Probabilistic inference for ODEs and SDEs · 2 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
replace Euler-Maruyama sampling with moment matchinglatent SDE on rotating MNIST · Rotating MNISTMSE: 0.046 -> 0.051Hurt
replace Euler-Maruyama sampling with linearizationlatent SDE on rotating MNIST · Rotating MNISTMSE: 0.046 -> 0.052Hurt
replace Euler-Maruyama sampling with moment matchinglatent SDE on rotating MNIST · Rotating MNISTNLPD (t=64): 33.0 -> 52.7Hurt
replace Euler-Maruyama sampling with linearizationlatent SDE on rotating MNIST · Rotating MNISTNLPD (t=64): 33.0 -> 54.5Hurt
use assumed density (linearization) instead of 1 Euler-Maruyama path, GPUlatent SDE · MOCAP wall-clock GPUtime (s): 37.1 -> 2.1Improved
use assumed density (linearization) instead of 200 Euler-Maruyama paths, CPUlatent SDE · MOCAP wall-clock CPUtime (s): 94.2 -> 1.8Improved
use moment matching instead of linearization, GPUassumed density SDE · MOCAP wall-clock GPUtime (s): 2.1 -> 6.0Hurt
use moment matching instead of linearization, CPUassumed density SDE · MOCAP wall-clock CPUtime (s): 1.8 -> 1.8No clear effect
use assumed density approximation instead of Latent SDE samplinglatent SDE · MOCAP testtest MSE: 4.03 -> 7.55Hurt
use assumed density approximation instead of Latent ODElatent SDE · MOCAP testtest MSE: 5.98 -> 7.55Hurt
use assumed density approximation instead of ODE2VAE-KLlatent SDE · MOCAP testtest MSE: 8.09 -> 7.55Improved
Euler-Maruyama paths needed to match moment matching accuracy, d=10 vs d=500Euler-Maruyama · Benes SDEnumber of trajectories: 25 -> 550Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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