10 citations · 15 across the 3 of their papers we have counts for
3 papers
cs.LG2021★ 5 cited
Equinox: neural networks in JAX via callable PyTrees and filtered transformations
Patrick Kidger, Cristian Garcia
JAX and PyTorch are two popular Python autodifferentiation frameworks. JAX is based around pure functions and functional programming. PyTorch has popularised the use of an object-o…
cs.LG2021★ 10 cited
Neural Controlled Differential Equations for Online Prediction Tasks
James Morrill, Patrick Kidger, Lingyi Yang +1
Neural controlled differential equations (Neural CDEs) are a continuous-time extension of recurrent neural networks (RNNs), achieving state-of-the-art (SOTA) performance at modelli…
math.CA2020
The degree- polynomials are the most difficult functions to uniformly approximate with degree- polynomials
Patrick Kidger
There exist well-known tight bounds on the error between a function and its best polynomial approximation of degree . We show that the error meets t…