Skip to content
AI Atlas
PaperActive

Deep operator learning for efficient sampling from invariant measures of stochastic differential equations

arxiv.org/abs/2609.11376

quality89

Updated 3 h ago · first seen 11 Sept 2026

paper_01M294FQX2NGSR66RC46MVMCYX

Published
11 Sept 2026
T1 · 3 h ago
arXiv
2609.11376
T1 · 3 h ago
Category
math.NA
T1 · 3 h ago

Abstract

We introduce an amortized neural sampler that combines operator learning with flow methods for sampling. It maps SDE coefficient functions to pushforwards from a reference measure to the invariant measures, enabling efficient sampling across families of stochastic differential equations. Our framework shifts traditional sampling cost to an initial training phase, after which new SDE instances require only one encoder pass and a few ODE solver steps, independent of mixing time. To handle problems in high dimensions, we use Lagrangian trajectory sensors for the coefficient functions and cross attention in the architecture. We also theoretically establish the expressivity and resolution invariance of our framework. Experiments on 1D and 2D SDE families show competitive accuracy with substantial speedups over MCMC in regimes with slow mixing, transfer across sensor counts, and demonstration results on a 64D interacting particle SDE where traditional grid approaches are infeasible.

Authors 3

Lin Guo, Li Lei, Jingtong Zhang

Specification

Official page

Source:arXiv (Atom API + RSS)T1observed 3 h agohigh

Arxiv announce type
cross

Source:arXiv (Atom API + RSS)T1observed 3 h agohigh

arXiv id
2609.11376

Source:arXiv (Atom API + RSS)T1observed 3 h agohigh

Categories
math.NA, cs.LG, cs.NA

Source:arXiv (Atom API + RSS)T1observed 3 h agohigh

PDF

Source:arXiv (Atom API + RSS)T1observed 3 h agohigh

Primary category
math.NA

Source:arXiv (Atom API + RSS)T1observed 3 h agohigh

Published
11 Sept 2026

Source:arXiv (Atom API + RSS)T1observed 3 h agohigh

Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →

Provenance

Attributed facts

9

Source tiers

T19

Freshest observation

3 h ago

Conflicts

None