Patrick Kidger

26 papers A* 8Journal 18
YearRankTypeTitle / Venue / Authors
2025 J jnl
AlgoTune: Can Language Models Speed Up General-Purpose Numerical Programs?
CoRR
Ori Press, Brandon Amos, Haoyu Zhao, Yikai Wu, Samuel K. Ainsworth, Dominik Krupke, Patrick Kidger, Touqir Sajed, Bartolomeo Stellato, Jisun Park, Nathanael Bosch, Eli Meril, Albert Steppi, Arman Zharmagambetov, Fangzhao Zhang, David Perez-Pineiro, Alberto Mercurio, Ni Zhan, Talor Abramovich, Kilian Lieret, Hanlin Zhang, Shirley Huang, Matthias Bethge, Ofir Press
2024 J jnl
Optimistix: modular optimisation in JAX and Equinox.
CoRR
Jason Rader, Terry J. Lyons, Patrick Kidger
2024 J jnl
Single-seed generation of Brownian paths and integrals for adaptive and high order SDE solvers.
CoRR
Andraz Jelincic, James Foster, Patrick Kidger
2023 J jnl
Lineax: unified linear solves and linear least-squares in JAX and Equinox.
CoRR
Jason Rader, Terry J. Lyons, Patrick Kidger
2022 J jnl
On Neural Differential Equations.
CoRR
Patrick Kidger
2022 J jnl
On the Choice of Interpolation Scheme for Neural CDEs.
Trans. Mach. Learn. Res.
James Morrill, Patrick Kidger, Lingyi Yang, Terry J. Lyons
2021 A* conf
"Hey, that's not an ODE": Faster ODE Adjoints via Seminorms.
ICML
Patrick Kidger, Ricky T. Q. Chen, Terry J. Lyons
2021 A* conf
Efficient and Accurate Gradients for Neural SDEs.
NeurIPS
Patrick Kidger, James Foster, Xuechen Li, Terry J. Lyons
2021 J jnl
Efficient and Accurate Gradients for Neural SDEs.
CoRR
Patrick Kidger, James Foster, Xuechen Li, Terry J. Lyons
2021 J jnl
Equinox: neural networks in JAX via callable PyTrees and filtered transformations.
CoRR
Patrick Kidger, Cristian Garcia
2021 J jnl
Neural Controlled Differential Equations for Online Prediction Tasks.
CoRR
James Morrill, Patrick Kidger, Lingyi Yang, Terry J. Lyons
2021 A* conf
Neural Rough Differential Equations for Long Time Series.
ICML
James Morrill, Cristopher Salvi, Patrick Kidger, James Foster
2021 A* conf
Neural SDEs as Infinite-Dimensional GANs.
ICML
Patrick Kidger, James Foster, Xuechen Li, Terry J. Lyons
2021 J jnl
Neural SDEs as Infinite-Dimensional GANs.
CoRR
Patrick Kidger, James Foster, Xuechen Li, Harald Oberhauser, Terry J. Lyons
2021 A* conf
Signatory: differentiable computations of the signature and logsignature transforms, on both CPU and GPU.
ICLR
Patrick Kidger, Terry J. Lyons
2020 J jnl
"Hey, that's not an ODE": Faster ODE Adjoints with 12 Lines of Code.
CoRR
Patrick Kidger, Ricky T. Q. Chen, Terry J. Lyons
2020 J jnl
A Generalised Signature Method for Time Series.
CoRR
James Morrill, Adeline Fermanian, Patrick Kidger, Terry J. Lyons
2020 J jnl
Generalised Interpretable Shapelets for Irregular Time Series.
CoRR
Patrick Kidger, James Morrill, Terry J. Lyons
2020 J jnl
Neural CDEs for Long Time Series via the Log-ODE Method.
CoRR
James Morrill, Patrick Kidger, Cristopher Salvi, James Foster, Terry J. Lyons
2020 A* conf
Neural Controlled Differential Equations for Irregular Time Series.
NeurIPS
Patrick Kidger, James Morrill, James Foster, Terry J. Lyons
2020 J jnl
Neural Controlled Differential Equations for Irregular Time Series.
CoRR
Patrick Kidger, James Morrill, James Foster, Terry J. Lyons
2020 J jnl
Signatory: differentiable computations of the signature and logsignature transforms, on both CPU and GPU.
CoRR
Patrick Kidger, Terry J. Lyons
2020 A* conf
Universal Approximation with Deep Narrow Networks.
COLT
Patrick Kidger, Terry J. Lyons
2019 A* conf
Deep Signature Transforms.
NeurIPS
Patrick Kidger, Patric Bonnier, Imanol Pérez Arribas, Cristopher Salvi, Terry J. Lyons
2019 J jnl
Deep Signatures.
CoRR
Patric Bonnier, Patrick Kidger, Imanol Pérez Arribas, Cristopher Salvi, Terry J. Lyons
2019 J jnl
Universal Approximation with Deep Narrow Networks.
CoRR
Patrick Kidger, Terry J. Lyons