Neural SDEs as Infinite-Dimensional GANs
read the original abstract
Stochastic differential equations (SDEs) are a staple of mathematical modelling of temporal dynamics. However, a fundamental limitation has been that such models have typically been relatively inflexible, which recent work introducing Neural SDEs has sought to solve. Here, we show that the current classical approach to fitting SDEs may be approached as a special case of (Wasserstein) GANs, and in doing so the neural and classical regimes may be brought together. The input noise is Brownian motion, the output samples are time-evolving paths produced by a numerical solver, and by parameterising a discriminator as a Neural Controlled Differential Equation (CDE), we obtain Neural SDEs as (in modern machine learning parlance) continuous-time generative time series models. Unlike previous work on this problem, this is a direct extension of the classical approach without reference to either prespecified statistics or density functions. Arbitrary drift and diffusions are admissible, so as the Wasserstein loss has a unique global minima, in the infinite data limit any SDE may be learnt. Example code has been made available as part of the \texttt{torchsde} repository.
This paper has not been read by Pith yet.
Forward citations
Cited by 4 Pith papers
-
Data-Driven Weak-form Discovery of Stochastic Systems
A weak-form stochastic SINDy algorithm using spatial Gaussian test functions recovers nonlinear terms in SDEs from data with coefficient errors below 4% on standard benchmarks.
-
Generative Path-Law Jump-Diffusion: Sequential MMD-Gradient Flows and Generalisation Bounds in Marcus-Signature RKHS
The paper proposes the ANJD flow and AVNSG operator to generate càdlàg trajectories via sequential MMD-gradient descent in Marcus-signature RKHS with generalisation bounds.
-
Anticipatory Reinforcement Learning: From Generative Path-Laws to Distributional Value Functions
ARL lifts states into signature-augmented manifolds and employs self-consistent proxies of future path-laws to enable deterministic expected-return evaluation while preserving contraction mappings in jump-diffusion en...
-
Data-Driven Weak-form Discovery of Stochastic Systems
A weak-form regression framework using spatial Gaussian kernels removes bias in recovering drift b(x) and diffusion a(x) for stochastic generators from single sparse regressions, validated on benchmarks with low coeff...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.