| Cheap Orthogonal Constraints in Neural Networks: A Simple Parametrization of the Orthogonal and Unitary Group M Lezcano-Casado, D Martínez-Rubio 36th International Conference on Machine Learning 97 (Proceedings of Machine …, 2019 | 201 | 2019 |
| Trivializations for gradient-based optimization on manifolds M Lezcano-Casado Advances in Neural Information Processing Systems (NeurIPS), 9154-9164, 2019 | 115 | 2019 |
| Improving normalizing flows via better orthogonal parameterizations A Golinski, M Lezcano-Casado, T Rainforth ICML Workshop on Invertible Neural Networks and Normalizing Flows, 2019 | 13 | 2019 |
| Improvements to Inference Compilation for Probabilistic Programming in Large-Scale Scientific Simulators M Lezcano-Casado, AG Baydin, DM Rubio, TA Le, F Wood, L Heinrich, ... Deep Learning for Physical Sciences workshop (NeurIPS, 2017 | 10* | 2017 |
| Curvature-dependant global convergence rates for optimization on manifolds of bounded geometry M Lezcano-Casado arXiv preprint arXiv:2008.02517, 2020 | 9 | 2020 |
| Adaptive and momentum methods on manifolds through trivializations M Lezcano-Casado arXiv preprint arXiv:2010.04617, 2020 | 7 | 2020 |
| PyTorch 2: Faster Machine Learning Through Dynamic Python Bytecode Transformation and Graph Compilation J Ansel, E Yang, H He, N Gimelshein, A Jain, M Voznesensky, B Bao, ... | 4 | 2024 |
| Geometric optimisation on manifolds with applications to deep learning M Lezcano-Casado arXiv preprint arXiv:2203.04794, 2022 | 4 | 2022 |
| Compiled inference with probabilistic programming for large-scale scientific simulations M Lezcano-Casado University of Oxford, 2017 | 3 | 2017 |
| Python Array API Standard: Toward Array Interoperability in the Scientific Python Ecosystem A Meurer, A Reines, R Gommers, YLL Fang, J Kirkham, M Barber, ... | | 2023 |
| Automatic Differentiation: Theory and Practice M Lezcano-Casado arXiv preprint arXiv:2207.06114, 2022 | | 2022 |
David Martínez-RubioZuse Institute BerlinVerified email at zib.de
