activity
20192022
most citedOn Neural Differential Equations

123 citations · 129 across the 2 of their papers we have counts for

collaborators
Showing cs.LGShow all

9 papers · 1 filter

cs.LG2022123 cited

On Neural Differential Equations

Patrick Kidger

The conjoining of dynamical systems and deep learning has become a topic of great interest. In particular, neural differential equations (NDEs) demonstrate that neural networks and…

cs.LG2021

Efficient and Accurate Gradients for Neural SDEs

Patrick Kidger, James Foster, Xuechen Li +1

Neural SDEs combine many of the best qualities of both RNNs and SDEs: memory efficient training, high-capacity function approximation, and strong priors on model space. This makes…

cs.LG2021

Neural SDEs as Infinite-Dimensional GANs

Patrick Kidger, James Foster, Xuechen Li +2

Stochastic differential equations (SDEs) are a staple of mathematical modelling of temporal dynamics. However, a fundamental limitation has been that such models have typically bee…

cs.LG2020

A Generalised Signature Method for Multivariate Time Series Feature Extraction

James Morrill, Adeline Fermanian, Patrick Kidger +1

The 'signature method' refers to a collection of feature extraction techniques for multivariate time series, derived from the theory of controlled differential equations. There is…

cs.LG20206 cited

Generalised Interpretable Shapelets for Irregular Time Series

Patrick Kidger, James Morrill, Terry Lyons

The shapelet transform is a form of feature extraction for time series, in which a time series is described by its similarity to each of a collection of `shapelets'. However it has…

cs.LG2020

Neural Controlled Differential Equations for Irregular Time Series

Patrick Kidger, James Morrill, James Foster +1

Neural ordinary differential equations are an attractive option for modelling temporal dynamics. However, a fundamental issue is that the solution to an ordinary differential equat…