Neural Controlled Differential Equations for Irregular Time Series P Kidger, J Morrill, J Foster, T Lyons Advances in Neural Information Processing Systems 33, 6696--6707, 2020 | 345 | 2020 |
Universal approximation with deep narrow networks P Kidger, T Lyons Conference on Learning Theory, 2306-2327, 2020 | 303 | 2020 |
On Neural Differential Equations P Kidger Doctoral Thesis, 2022 | 126 | 2022 |
Neural Rough Differential Equations for Long Time Series J Morrill, C Salvi, P Kidger, J Foster, T Lyons International Conference on Machine Learning, 2021 | 93* | 2021 |
Neural SDEs as Infinite-Dimensional GANs P Kidger, J Foster, X Li, H Oberhauser, T Lyons International Conference on Machine Learning, 2021 | 91 | 2021 |
Signatory: differentiable computations of the signature and logsignature transforms, on both CPU and GPU P Kidger, T Lyons International Conference on Learning Representations, 2021 | 79 | 2021 |
Deep signature transforms P Kidger, P Bonnier, I Perez Arribas, C Salvi, T Lyons Advances in Neural Information Processing Systems 32, 3105-3115, 2019 | 72 | 2019 |
“Hey, that’s not an ODE”: Faster ODE Adjoints via Seminorms P Kidger, RTQ Chen, T Lyons International Conference on Machine Learning, 2021 | 41* | 2021 |
A Generalised Signature Method for Multivariate Time Series Feature Extraction J Morrill, A Fermanian, P Kidger, T Lyons arXiv preprint arXiv:2006.00873, 2020 | 40* | 2020 |
On the choice of interpolation scheme for neural CDEs J Morrill, P Kidger, L Yang, T Lyons Transactions on Machine Learning Research 2022 (9), 2022 | 36* | 2022 |
Efficient and Accurate Gradients for Neural SDEs P Kidger, J Foster, X Li, T Lyons Advances in Neural Information Processing Systems 34, 2021 | 28 | 2021 |
Equinox: neural networks in JAX via callable PyTrees and filtered transformations P Kidger, C Garcia Differentiable Programming workshop, Neural Information Processing Systems 2021, 2021 | 25 | 2021 |
Generalised Interpretable Shapelets for Irregular Time Series P Kidger, J Morrill, T Lyons arXiv preprint arXiv:2005.13948, 2020 | 9 | 2020 |