Timezone: »
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 \textit{any} SDE may be learnt.
Author Information
Patrick Kidger (University of Oxford)
Maths+ML PhD student at Oxford. Neural ODEs+SDEs+CDEs, time series, rough analysis. (Also ice skating, martial arts and scuba diving!)
James Foster (University of Oxford)
Xuechen Li (University of Toronto)
Terry Lyons (University of Oxford)
Related Events (a corresponding poster, oral, or spotlight)
-
2021 Poster: Neural SDEs as Infinite-Dimensional GANs »
Thu. Jul 22nd 04:00 -- 06:00 AM Room
More from the Same Authors
-
2023 Poster: Sampling-based Nyström Approximation and Kernel Quadrature »
Satoshi Hayakawa · Harald Oberhauser · Terry Lyons -
2021 Poster: SigGPDE: Scaling Sparse Gaussian Processes on Sequential Data »
Maud Lemercier · Cristopher Salvi · Thomas Cass · Edwin V. Bonilla · Theodoros Damoulas · Terry Lyons -
2021 Spotlight: SigGPDE: Scaling Sparse Gaussian Processes on Sequential Data »
Maud Lemercier · Cristopher Salvi · Thomas Cass · Edwin V. Bonilla · Theodoros Damoulas · Terry Lyons -
2021 Poster: Neural Rough Differential Equations for Long Time Series »
James Morrill · Cristopher Salvi · Patrick Kidger · James Foster -
2021 Spotlight: Neural Rough Differential Equations for Long Time Series »
James Morrill · Cristopher Salvi · Patrick Kidger · James Foster -
2021 Poster: "Hey, that's not an ODE": Faster ODE Adjoints via Seminorms »
Patrick Kidger · Ricky T. Q. Chen · Terry Lyons -
2021 Spotlight: "Hey, that's not an ODE": Faster ODE Adjoints via Seminorms »
Patrick Kidger · Ricky T. Q. Chen · Terry Lyons