Joan Alexis Glaunès
Research Subjects
Joan Alexis Glaunès has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Benjamin Charlier
IMAG, Universite de Montpelier, CNRS
2 shared publications - François-David Collin2 shared publications
- Ghislain Durif
Institut Montpelliérain Alexander Grothendieck CNRS Université de Montpellier France
2 shared publications - Jean Feydy
DMA Ecole normale supérieure Paris France
2 shared publications - Anton François
Université de Paris-Cité
1 shared publication Catherine Oppenheim
UMR 1266 INSERM, IMA-BRAIN, IPNP
1 shared publication
Latest Publications
- 9 July 2022
- Published by Springer Nature
- p. 8-17
Weighted Metamorphosis for Registration of Images with Different Topologies
- 9 July 2022
- Published by Springer Nature
- p. 8-17
Weighted Metamorphosis for Registration of Images with Different Topologies
- Open Access
Kernel Operations on the GPU, with Autodiff, without Memory Overflows
The KeOps library provides a fast and memory-efficient GPU support for tensors whose entries are given by a mathematical formula, such as kernel and distance matrices. KeOps alleviates the major bottleneck of tensor-centric libraries for kernel and geometric applications: memory consumption. It also supports automatic differentiation and outperforms standard GPU baselines, including PyTorch CUDA tensors or the Halide and TVM libraries. KeOps combines optimized C++/CUDA schemes with binders for high-level languages: Python (Numpy and PyTorch), Matlab and GNU R. As a result, high-level "quadratic" codes can now scale up to large data sets with millions of samples processed in seconds. KeOps brings graphics-like performances for kernel methods and is freely available on standard repositories (PyPi, CRAN). To showcase its versatility, we provide tutorials in a wide range of settings online at \url{www.kernel-operations.io}.
Open AccessKernel Operations on the GPU, with Autodiff, without Memory Overflows
The KeOps library provides a fast and memory-efficient GPU support for tensors whose entries are given by a mathematical formula, such as kernel and distance matrices. KeOps alleviates the major bottleneck of tensor-centric libraries for kernel and geometric applications: memory consumption. It also supports automatic differentiation and outperforms standard GPU baselines, including PyTorch CUDA tensors or the Halide and TVM libraries. KeOps combines optimized C++/CUDA schemes with binders for high-level languages: Python (Numpy and PyTorch), Matlab and GNU R. As a result, high-level "quadratic" codes can now scale up to large data sets with millions of samples processed in seconds. KeOps brings graphics-like performances for kernel methods and is freely available on standard repositories (PyPi, CRAN). To showcase its versatility, we provide tutorials in a wide range of settings online at \url{www.kernel-operations.io}.
- Open Access
Kernel Operations on GPU, without memory overflows Kernel Operations on the GPU, with Autodiff, without Memory Overflows
The KeOps library provides a fast and memory-efficient GPU support for tensors whose entries are given by a mathematical formula, such as kernel and distance matrices. KeOps alleviates the major bottleneck of tensor-centric libraries for kernel and geometric applications: memory consumption. It also supports automatic differentiation and outperforms standard GPU baselines, including PyTorch CUDA tensors or the Halide and TVM libraries. KeOps combines optimized C++/CUDA schemes with binders for high-level languages: Python (Numpy and PyTorch), Matlab and GNU R. As a result, high-level "quadratic" codes can now scale up to large data sets with millions of samples processed in seconds. KeOps brings graphics-like performances for kernel methods and is freely available on standard repositories (PyPi, CRAN). To showcase its versatility, we provide tutorials in a wide range of settings online at www.kernel-operations.io.
Open AccessKernel Operations on GPU, without memory overflows Kernel Operations on the GPU, with Autodiff, without Memory Overflows
The KeOps library provides a fast and memory-efficient GPU support for tensors whose entries are given by a mathematical formula, such as kernel and distance matrices. KeOps alleviates the major bottleneck of tensor-centric libraries for kernel and geometric applications: memory consumption. It also supports automatic differentiation and outperforms standard GPU baselines, including PyTorch CUDA tensors or the Halide and TVM libraries. KeOps combines optimized C++/CUDA schemes with binders for high-level languages: Python (Numpy and PyTorch), Matlab and GNU R. As a result, high-level "quadratic" codes can now scale up to large data sets with millions of samples processed in seconds. KeOps brings graphics-like performances for kernel methods and is freely available on standard repositories (PyPi, CRAN). To showcase its versatility, we provide tutorials in a wide range of settings online at www.kernel-operations.io.