CircleCI update of dev docs (4006).

Author: Circle CI

master/_downloads/06f3dd7c3258690ab730be0a658b5e36/plot_ssw_unif_torch.zip

@@ -15,7 +15,7 @@
       },
       "outputs": [],
       "source": [
-        "# Author: Paul Krzakala <paul.krzakala@gmail.com>\n# License: MIT License\n\n# sphinx_gallery_thumbnail_number = 1"
+        "# Author: Paul Krzakala <paul.krzakala@gmail.com>\n#         Thibaut Germain <thibaut.germain.pro@gmail.com>\n# License: MIT License\n\n# sphinx_gallery_thumbnail_number = 1"
       ]
     },
     {
@@ -40,7 +40,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## Solving the Problems\n\nOnce the cost matrices are computed, we can solve the corresponding\noptimal transport problems.\n\n<div class=\"alert alert-info\"><h4>Note</h4><p>One option is to solve them sequentially with a Python loop using\n   :func:`ot.solve`.\n   This is simple but inefficient for large batches.</p></div>\n\nInstead, you can use :func:`ot.batch.solve_batch`, which solves all\nproblems in parallel.\n\n"
+        "## Solving the Problems\n\nOnce the cost matrices are computed, we can solve the corresponding\noptimal transport problems.\n\n<div class=\"alert alert-info\"><h4>Note</h4><p>One option is to solve them sequentially with a Python loop using\n   :func:`ot.solve`.\n   This is simple but inefficient for large batches.</p></div>\n\nInstead, you can use :func:`ot.batch.solve_batch`, which solves all\nproblems in parallel. Several methods are available: [\"sinkhorn\", \"log_sinkhorn\"]\nwhich solve regularized OT problems, and [\"proximal\"] which\nsolves regularized and unregularized OT problem using a proximal point scheme.\nBy default, the method is set to \"auto\" which automatically selects the appropriate\nmethod based on the value of `reg`. If `reg` is None or 0, the proximal point method\nis used. If `reg` is greater than 0, the Sinkhorn algorithm is used.\n\n"
       ]
     },
     {
@@ -51,7 +51,7 @@
       },
       "outputs": [],
       "source": [
-        "reg = 1.0\nmax_iter = 100\ntol = 1e-3\n\n# Naive approach\nresults_values_list = []\nfor i in range(n_problems):\n    res = ot.solve(M_list[i], reg=reg, max_iter=max_iter, tol=tol, reg_type=\"entropy\")\n    results_values_list.append(res.value_linear)\n\n# Batched approach\nresults_batch = ot.solve_batch(\n    M=M_batch, reg=reg, max_iter=max_iter, tol=tol, reg_type=\"entropy\"\n)\nresults_values_batch = results_batch.value_linear\n\nassert np.allclose(np.array(results_values_list), results_values_batch, atol=tol * 10)"
+        "max_iter = 10000\ntol = 1e-4\n\n# Classical OT problem\n## Naive approach\nresults_values_list = []\nfor i in range(n_problems):\n    res = ot.solve(M_list[i], max_iter=max_iter, tol=tol)\n    results_values_list.append(res.value_linear)\n\n## Batched approach\nresults_batch = ot.solve_batch(M=M_batch, max_iter=max_iter, tol=tol)\nresults_values_batch = results_batch.value_linear\n\nexact_validated = np.allclose(\n    np.array(results_values_list), results_values_batch, atol=tol * 10\n)\n\n# Entropic regularized OT problem\n## Naive approach\nreg = 1.0\nresults_values_list = []\nfor i in range(n_problems):\n    res = ot.solve(M_list[i], reg=reg, max_iter=max_iter, tol=tol, reg_type=\"entropy\")\n    results_values_list.append(res.value_linear)\n\n## Batched approach\nresults_batch = ot.solve_batch(\n    M=M_batch, reg=reg, max_iter=max_iter, tol=tol, reg_type=\"entropy\"\n)\nresults_values_batch = results_batch.value_linear\n\nentropic_validated = np.allclose(\n    np.array(results_values_list), results_values_batch, atol=tol * 10\n)\n\nprint(\n    f\"Exact solve vs proximal batch close: {exact_validated} \\nSinkhorn solve vs Sinkhorn solve_batch close: {entropic_validated}\"\n)"
       ]
     },
     {