summaryrefslogtreecommitdiff
path: root/docs
diff options
context:
space:
mode:
authorRémi Flamary <remi.flamary@gmail.com>2019-06-27 14:34:23 +0200
committerRémi Flamary <remi.flamary@gmail.com>2019-06-27 14:34:23 +0200
commitd20d471a1806bde43c23e67c1f805aa3c8908ec3 (patch)
treedb40ba091643cd6945c087d583bbd8856d8c9767 /docs
parent8ae85fd6b3649058da07b16c9ea139864c7f94a1 (diff)
update part 1
Diffstat (limited to 'docs')
-rw-r--r--docs/source/quickstart.rst23
1 files changed, 23 insertions, 0 deletions
diff --git a/docs/source/quickstart.rst b/docs/source/quickstart.rst
index d8d4838..a14358c 100644
--- a/docs/source/quickstart.rst
+++ b/docs/source/quickstart.rst
@@ -83,6 +83,29 @@ properties. It can computed from an already estimated OT matrix with
Regularized Optimal Transport
-----------------------------
+Recent developments have shown the interest of regularized OT both in terms of
+computational and statistical properties.
+
+We address in this section the regularized OT problem that can be expressed as
+
+.. math::
+ \gamma^* = arg\min_\gamma <\gamma,M>_F + reg*\Omega(\gamma)
+
+ s.t. \gamma 1 = a
+
+ \gamma^T 1= b
+
+ \gamma\geq 0
+where :
+
+- :math:`M\in\mathbb{R}_+^{m\times n}` is the metric cost matrix defining the cost to move mass from bin :math:`a_i` to bin :math:`b_j`.
+- :math:`a` and :math:`b` are histograms (positive, sum to 1) that represent the weights of each samples in the source an target distributions.
+- :math:`\Omega` is the regularization term.
+
+We disvuss in the following specific algorithms
+
+
+
Entropic regularized OT
^^^^^^^^^^^^^^^^^^^^^^^