From eb7a395c8afb71d51e58c286e216602505a496f0 Mon Sep 17 00:00:00 2001 From: Rémi Flamary Date: Mon, 24 Sep 2018 10:08:00 +0200 Subject: add reference in readme --- README.md | 2 ++ 1 file changed, 2 insertions(+) (limited to 'README.md') diff --git a/README.md b/README.md index 1d3b097..2ebb15c 100644 --- a/README.md +++ b/README.md @@ -228,3 +228,5 @@ You can also post bug reports and feature requests in Github issues. Make sure t [19] Seguy, V., Bhushan Damodaran, B., Flamary, R., Courty, N., Rolet, A.& Blondel, M. [Large-scale Optimal Transport and Mapping Estimation](https://arxiv.org/pdf/1711.02283.pdf). International Conference on Learning Representation (2018) [20] Cuturi, M. and Doucet, A. (2014) [Fast Computation of Wasserstein Barycenters](http://proceedings.mlr.press/v32/cuturi14.html). International Conference in Machine Learning + +[21] J. Altschuler, J.Weed, P. Rigollet, (2017) Near-linear time approximation algorithms for optimal transport via Sinkhorn iteration, Advances in Neural Information Processing Systems (NIPS) 31 \ No newline at end of file -- cgit v1.2.3 From ff824a22d232b68ddffcb13b976d75a5b8bc03e5 Mon Sep 17 00:00:00 2001 From: Rémi Flamary Date: Mon, 24 Sep 2018 10:08:18 +0200 Subject: add reference in readme --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'README.md') diff --git a/README.md b/README.md index 2ebb15c..6a6686c 100644 --- a/README.md +++ b/README.md @@ -14,7 +14,7 @@ This open source Python library provide several solvers for optimization problem It provides the following solvers: * OT Network Flow solver for the linear program/ Earth Movers Distance [1]. -* Entropic regularization OT solver with Sinkhorn Knopp Algorithm [2] and stabilized version [9][10] with optional GPU implementation (requires cudamat). +* Entropic regularization OT solver with Sinkhorn Knopp Algorithm [2] and stabilized version [9][10] and greedy SInkhorn [21] with optional GPU implementation (requires cudamat). * Smooth optimal transport solvers (dual and semi-dual) for KL and squared L2 regularizations [17]. * Non regularized Wasserstein barycenters [16] with LP solver (only small scale). * Bregman projections for Wasserstein barycenter [3] and unmixing [4]. -- cgit v1.2.3 From 24a53ef2dba0a43c282f6b31937c3e7901df7930 Mon Sep 17 00:00:00 2001 From: Rémi Flamary Date: Mon, 24 Sep 2018 10:17:21 +0200 Subject: add contributor --- README.md | 1 + ot/bregman.py | 4 ++-- 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'README.md') diff --git a/README.md b/README.md index 6a6686c..4d824ce 100644 --- a/README.md +++ b/README.md @@ -165,6 +165,7 @@ The contributors to this library are: * [Antoine Rolet](https://arolet.github.io/) * Erwan Vautier (Gromov-Wasserstein) * [Kilian Fatras](https://kilianfatras.github.io/) +* [Alain Rakotomamonjy](https://sites.google.com/site/alainrakotomamonjy/home) This toolbox benefit a lot from open source research and we would like to thank the following persons for providing some code (in various languages): diff --git a/ot/bregman.py b/ot/bregman.py index faa6365..97027e8 100644 --- a/ot/bregman.py +++ b/ot/bregman.py @@ -536,7 +536,7 @@ def greenkhorn(a, b, M, reg, numItermax=10000, stopThr=1e-9, verbose=False, log= G[i_1, :] = u[i_1] * K[i_1, :] * v viol[i_1] = u[i_1] * K[i_1, :].dot(v) - a[i_1] - viol_2 = viol_2 + (K[i_1, :].T * (u[i_1] - old_u) * v) + viol_2 += (K[i_1, :].T * (u[i_1] - old_u) * v) else: old_v = v[i_2] @@ -544,7 +544,7 @@ def greenkhorn(a, b, M, reg, numItermax=10000, stopThr=1e-9, verbose=False, log= G[:, i_2] = u * K[:, i_2] * v[i_2] #aviol = (G@one_m - a) #aviol_2 = (G.T@one_n - b) - viol = viol + (-old_v + v[i_2]) * K[:, i_2] * u + viol += (-old_v + v[i_2]) * K[:, i_2] * u viol_2[i_2] = v[i_2] * K[:, i_2].dot(u) - b[i_2] #print('b',np.max(abs(aviol -viol)),np.max(abs(aviol_2 - viol_2))) -- cgit v1.2.3 From dee6d6e16f6e5d328bc590089cf99ef586d7ca0f Mon Sep 17 00:00:00 2001 From: Rémi Flamary Date: Mon, 24 Sep 2018 10:34:32 +0200 Subject: correct reference number in doc --- README.md | 2 +- ot/bregman.py | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'README.md') diff --git a/README.md b/README.md index 1c8114a..16fa153 100644 --- a/README.md +++ b/README.md @@ -232,4 +232,4 @@ You can also post bug reports and feature requests in Github issues. Make sure t [21] Solomon, J., De Goes, F., Peyré, G., Cuturi, M., Butscher, A., Nguyen, A. & Guibas, L. (2015). [Convolutional wasserstein distances: Efficient optimal transportation on geometric domains](https://dl.acm.org/citation.cfm?id=2766963). ACM Transactions on Graphics (TOG), 34(4), 66. -[21] J. Altschuler, J.Weed, P. Rigollet, (2017) [Near-linear time approximation algorithms for optimal transport via Sinkhorn iteration](https://papers.nips.cc/paper/6792-near-linear-time-approximation-algorithms-for-optimal-transport-via-sinkhorn-iteration.pdf), Advances in Neural Information Processing Systems (NIPS) 31 +[22] J. Altschuler, J.Weed, P. Rigollet, (2017) [Near-linear time approximation algorithms for optimal transport via Sinkhorn iteration](https://papers.nips.cc/paper/6792-near-linear-time-approximation-algorithms-for-optimal-transport-via-sinkhorn-iteration.pdf), Advances in Neural Information Processing Systems (NIPS) 31 diff --git a/ot/bregman.py b/ot/bregman.py index 418de57..fd04fa4 100644 --- a/ot/bregman.py +++ b/ot/bregman.py @@ -489,7 +489,7 @@ def greenkhorn(a, b, M, reg, numItermax=10000, stopThr=1e-9, verbose=False, log= ---------- .. [2] M. Cuturi, Sinkhorn Distances : Lightspeed Computation of Optimal Transport, Advances in Neural Information Processing Systems (NIPS) 26, 2013 - [21] J. Altschuler, J.Weed, P. Rigollet : Near-linear time approximation algorithms for optimal transport via Sinkhorn iteration, Advances in Neural Information Processing Systems (NIPS) 31, 2017 + [22] J. Altschuler, J.Weed, P. Rigollet : Near-linear time approximation algorithms for optimal transport via Sinkhorn iteration, Advances in Neural Information Processing Systems (NIPS) 31, 2017 See Also -- cgit v1.2.3 From 8f908bd3096d9bc57a05b3de1c37b97805a10959 Mon Sep 17 00:00:00 2001 From: Rémi Flamary Date: Mon, 24 Sep 2018 10:35:27 +0200 Subject: update readme+doc --- README.md | 4 ++-- docs/source/readme.rst | 38 +++++++++++++++++++++++++++++++++++--- 2 files changed, 37 insertions(+), 5 deletions(-) (limited to 'README.md') diff --git a/README.md b/README.md index 16fa153..67f62b3 100644 --- a/README.md +++ b/README.md @@ -14,10 +14,10 @@ This open source Python library provide several solvers for optimization problem It provides the following solvers: * OT Network Flow solver for the linear program/ Earth Movers Distance [1]. -* Entropic regularization OT solver with Sinkhorn Knopp Algorithm [2] and stabilized version [9][10] and greedy SInkhorn [21] with optional GPU implementation (requires cudamat). +* Entropic regularization OT solver with Sinkhorn Knopp Algorithm [2] and stabilized version [9][10] and greedy SInkhorn [22] with optional GPU implementation (requires cudamat). * Smooth optimal transport solvers (dual and semi-dual) for KL and squared L2 regularizations [17]. * Non regularized Wasserstein barycenters [16] with LP solver (only small scale). -* Bregman projections for Wasserstein barycenter [3] and unmixing [4]. +* Bregman projections for Wasserstein barycenter [3], convolutional barycenter [21] and unmixing [4]. * Optimal transport for domain adaptation with group lasso regularization [5] * Conditional gradient [6] and Generalized conditional gradient for regularized OT [7]. * Linear OT [14] and Joint OT matrix and mapping estimation [8]. diff --git a/docs/source/readme.rst b/docs/source/readme.rst index 5d37f64..a839231 100644 --- a/docs/source/readme.rst +++ b/docs/source/readme.rst @@ -13,13 +13,14 @@ It provides the following solvers: - OT Network Flow solver for the linear program/ Earth Movers Distance [1]. - Entropic regularization OT solver with Sinkhorn Knopp Algorithm [2] - and stabilized version [9][10] with optional GPU implementation - (requires cudamat). + and stabilized version [9][10] and greedy SInkhorn [22] with optional + GPU implementation (requires cudamat). - Smooth optimal transport solvers (dual and semi-dual) for KL and squared L2 regularizations [17]. - Non regularized Wasserstein barycenters [16] with LP solver (only small scale). -- Bregman projections for Wasserstein barycenter [3] and unmixing [4]. +- Bregman projections for Wasserstein barycenter [3], convolutional + barycenter [21] and unmixing [4]. - Optimal transport for domain adaptation with group lasso regularization [5] - Conditional gradient [6] and Generalized conditional gradient for @@ -29,6 +30,9 @@ It provides the following solvers: pymanopt). - Gromov-Wasserstein distances and barycenters ([13] and regularized [12]) +- Stochastic Optimization for Large-scale Optimal Transport (semi-dual + problem [18] and dual problem [19]) +- Non regularized free support Wasserstein barycenters [20]. Some demonstrations (both in Python and Jupyter Notebook format) are available in the examples folder. @@ -219,6 +223,9 @@ The contributors to this library are: - `Stanislas Chambon `__ - `Antoine Rolet `__ - Erwan Vautier (Gromov-Wasserstein) +- `Kilian Fatras `__ +- `Alain + Rakotomamonjy `__ This toolbox benefit a lot from open source research and we would like to thank the following persons for providing some code (in various @@ -334,6 +341,31 @@ Optimal Transport `__. Proceedings of the Twenty-First International Conference on Artificial Intelligence and Statistics (AISTATS). +[18] Genevay, A., Cuturi, M., Peyré, G. & Bach, F. (2016) `Stochastic +Optimization for Large-scale Optimal +Transport `__. Advances in Neural +Information Processing Systems (2016). + +[19] Seguy, V., Bhushan Damodaran, B., Flamary, R., Courty, N., Rolet, +A.& Blondel, M. `Large-scale Optimal Transport and Mapping +Estimation `__. International +Conference on Learning Representation (2018) + +[20] Cuturi, M. and Doucet, A. (2014) `Fast Computation of Wasserstein +Barycenters `__. +International Conference in Machine Learning + +[21] Solomon, J., De Goes, F., Peyré, G., Cuturi, M., Butscher, A., +Nguyen, A. & Guibas, L. (2015). `Convolutional wasserstein distances: +Efficient optimal transportation on geometric +domains `__. ACM +Transactions on Graphics (TOG), 34(4), 66. + +[22] J. Altschuler, J.Weed, P. Rigollet, (2017) `Near-linear time +approximation algorithms for optimal transport via Sinkhorn +iteration `__, +Advances in Neural Information Processing Systems (NIPS) 31 + .. |PyPI version| image:: https://badge.fury.io/py/POT.svg :target: https://badge.fury.io/py/POT .. |Anaconda Cloud| image:: https://anaconda.org/conda-forge/pot/badges/version.svg -- cgit v1.2.3