Patrick Kidger

According to our database, Patrick Kidger authored at least 20 papers between 2019 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2024

Optimistix: modular optimisation in JAX and Equinox.

Jason Rader, Terry J. Lyons, Patrick Kidger

CoRR, 2024

2023

Lineax: unified linear solves and linear least-squares in JAX and Equinox.

Jason Rader, Terry J. Lyons, Patrick Kidger

CoRR, 2023

2022

On the Choice of Interpolation Scheme for Neural CDEs.

James Morrill, Patrick Kidger, Lingyi Yang, Terry J. Lyons

Trans. Mach. Learn. Res., 2022

On Neural Differential Equations.

Patrick Kidger

CoRR, 2022

2021

Equinox: neural networks in JAX via callable PyTrees and filtered transformations.

Patrick Kidger, Cristian Garcia

CoRR, 2021

Neural Controlled Differential Equations for Online Prediction Tasks.

James Morrill, Patrick Kidger, Lingyi Yang, Terry J. Lyons

CoRR, 2021

Neural SDEs as Infinite-Dimensional GANs.

Patrick Kidger, James Foster, Xuechen Li, Harald Oberhauser, Terry J. Lyons

CoRR, 2021

Efficient and Accurate Gradients for Neural SDEs.

Patrick Kidger, James Foster, Xuechen Li, Terry J. Lyons

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Neural Rough Differential Equations for Long Time Series.

James Morrill, Cristopher Salvi, Patrick Kidger, James Foster

Proceedings of the 38th International Conference on Machine Learning, 2021

Neural SDEs as Infinite-Dimensional GANs.

Patrick Kidger, James Foster, Xuechen Li, Terry J. Lyons

Proceedings of the 38th International Conference on Machine Learning, 2021

"Hey, that's not an ODE": Faster ODE Adjoints via Seminorms.

Patrick Kidger, Ricky T. Q. Chen, Terry J. Lyons

Proceedings of the 38th International Conference on Machine Learning, 2021

Signatory: differentiable computations of the signature and logsignature transforms, on both CPU and GPU.

Patrick Kidger, Terry J. Lyons

Proceedings of the 9th International Conference on Learning Representations, 2021

2020

"Hey, that's not an ODE": Faster ODE Adjoints with 12 Lines of Code.

Patrick Kidger, Ricky T. Q. Chen, Terry J. Lyons

CoRR, 2020

Neural CDEs for Long Time Series via the Log-ODE Method.

James Morrill, Patrick Kidger, Cristopher Salvi, James Foster, Terry J. Lyons

CoRR, 2020

A Generalised Signature Method for Time Series.

James Morrill, Adeline Fermanian, Patrick Kidger, Terry J. Lyons

CoRR, 2020

Generalised Interpretable Shapelets for Irregular Time Series.

Patrick Kidger, James Morrill, Terry J. Lyons

CoRR, 2020

Neural Controlled Differential Equations for Irregular Time Series.

Patrick Kidger, James Morrill, James Foster, Terry J. Lyons

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Universal Approximation with Deep Narrow Networks.

Patrick Kidger, Terry J. Lyons

Proceedings of the Conference on Learning Theory, 2020

2019

Deep Signatures.

Patric Bonnier, Patrick Kidger, Imanol Pérez Arribas, Cristopher Salvi, Terry J. Lyons

CoRR, 2019

Deep Signature Transforms.

Patrick Kidger, Patric Bonnier, Imanol Pérez Arribas, Cristopher Salvi, Terry J. Lyons

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019