projection-losses
projection-losses copied to clipboard
Python implementation of projection losses.
.. -- mode: rst --
Projection losses
Python implementation of "Structured Prediction with Projection Oracles".
Supported polytopes
- Probability simplex
- Unit cube
- Knapsack polytope
- Birkhoff polytope
- Permutahedron
- Order simplex
- Cartesian products
Installation
Simply copy relevant files to your project.
References
.. [1] SparseMAP: Differentiable Sparse Structured Inference.
Vlad Niculae, André F. T. Martins, Mathieu Blondel, Claire Cardie.
In Proc. of ICML 2018.
[arXiv <https://arxiv.org/abs/1802.04223>
_]
.. [2] Learning Classifiers with Fenchel-Young Losses: Generalized Entropies, Margins, and Algorithms.
Mathieu Blondel, André F. T. Martins, Vlad Niculae.
In Proc. of AISTATS 2019.
[arXiv <https://arxiv.org/abs/1805.09717>
_]
.. [3] Learning with Fenchel-Young Losses.
Mathieu Blondel, André F. T. Martins, Vlad Niculae.
Preprint.
[arXiv <https://arxiv.org/abs/1901.02324>
_]
.. [4] Structured Prediction with Projection Oracles.
Mathieu Blondel.
In Proc. of NeurIPS 2019.
[arXiv <https://arxiv.org/abs/1910.11369>
_]
Author
- Mathieu Blondel, 2019