1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
|
# -*- coding: utf-8 -*-
"""
=================================================================================
1D Wasserstein barycenter comparison between exact LP and entropic regularization
=================================================================================
This example illustrates the computation of regularized Wasserstein Barycenter
as proposed in [3] and exact LP barycenters using standard LP solver.
It reproduces approximately Figure 3.1 and 3.2 from the following paper:
Cuturi, M., & Peyré, G. (2016). A smoothed dual approach for variational
Wasserstein problems. SIAM Journal on Imaging Sciences, 9(1), 320-343.
[3] Benamou, J. D., Carlier, G., Cuturi, M., Nenna, L., & Peyré, G. (2015).
Iterative Bregman projections for regularized transportation problems
SIAM Journal on Scientific Computing, 37(2), A1111-A1138.
"""
# Author: Remi Flamary <remi.flamary@unice.fr>
#
# License: MIT License
# sphinx_gallery_thumbnail_number = 4
import numpy as np
import matplotlib.pylab as pl
import ot
# necessary for 3d plot even if not used
from mpl_toolkits.mplot3d import Axes3D # noqa
from matplotlib.collections import PolyCollection # noqa
#import ot.lp.cvx as cvx
##############################################################################
# Gaussian Data
# -------------
#%% parameters
problems = []
n = 100 # nb bins
# bin positions
x = np.arange(n, dtype=np.float64)
# Gaussian distributions
# Gaussian distributions
a1 = ot.datasets.make_1D_gauss(n, m=20, s=5) # m= mean, s= std
a2 = ot.datasets.make_1D_gauss(n, m=60, s=8)
# creating matrix A containing all distributions
A = np.vstack((a1, a2)).T
n_distributions = A.shape[1]
# loss matrix + normalization
M = ot.utils.dist0(n)
M /= M.max()
#%% plot the distributions
pl.figure(1, figsize=(6.4, 3))
for i in range(n_distributions):
pl.plot(x, A[:, i])
pl.title('Distributions')
pl.tight_layout()
#%% barycenter computation
alpha = 0.5 # 0<=alpha<=1
weights = np.array([1 - alpha, alpha])
# l2bary
bary_l2 = A.dot(weights)
# wasserstein
reg = 1e-3
ot.tic()
bary_wass = ot.bregman.barycenter(A, M, reg, weights)
ot.toc()
ot.tic()
bary_wass2 = ot.lp.barycenter(A, M, weights, solver='interior-point', verbose=True)
ot.toc()
pl.figure(2)
pl.clf()
pl.subplot(2, 1, 1)
for i in range(n_distributions):
pl.plot(x, A[:, i])
pl.title('Distributions')
pl.subplot(2, 1, 2)
pl.plot(x, bary_l2, 'r', label='l2')
pl.plot(x, bary_wass, 'g', label='Reg Wasserstein')
pl.plot(x, bary_wass2, 'b', label='LP Wasserstein')
pl.legend()
pl.title('Barycenters')
pl.tight_layout()
problems.append([A, [bary_l2, bary_wass, bary_wass2]])
##############################################################################
# Stair Data
# ----------
#%% parameters
a1 = 1.0 * (x > 10) * (x < 50)
a2 = 1.0 * (x > 60) * (x < 80)
a1 /= a1.sum()
a2 /= a2.sum()
# creating matrix A containing all distributions
A = np.vstack((a1, a2)).T
n_distributions = A.shape[1]
# loss matrix + normalization
M = ot.utils.dist0(n)
M /= M.max()
#%% plot the distributions
pl.figure(1, figsize=(6.4, 3))
for i in range(n_distributions):
pl.plot(x, A[:, i])
pl.title('Distributions')
pl.tight_layout()
#%% barycenter computation
alpha = 0.5 # 0<=alpha<=1
weights = np.array([1 - alpha, alpha])
# l2bary
bary_l2 = A.dot(weights)
# wasserstein
reg = 1e-3
ot.tic()
bary_wass = ot.bregman.barycenter(A, M, reg, weights)
ot.toc()
ot.tic()
bary_wass2 = ot.lp.barycenter(A, M, weights, solver='interior-point', verbose=True)
ot.toc()
problems.append([A, [bary_l2, bary_wass, bary_wass2]])
pl.figure(2)
pl.clf()
pl.subplot(2, 1, 1)
for i in range(n_distributions):
pl.plot(x, A[:, i])
pl.title('Distributions')
pl.subplot(2, 1, 2)
pl.plot(x, bary_l2, 'r', label='l2')
pl.plot(x, bary_wass, 'g', label='Reg Wasserstein')
pl.plot(x, bary_wass2, 'b', label='LP Wasserstein')
pl.legend()
pl.title('Barycenters')
pl.tight_layout()
##############################################################################
# Dirac Data
# ----------
#%% parameters
a1 = np.zeros(n)
a2 = np.zeros(n)
a1[10] = .25
a1[20] = .5
a1[30] = .25
a2[80] = 1
a1 /= a1.sum()
a2 /= a2.sum()
# creating matrix A containing all distributions
A = np.vstack((a1, a2)).T
n_distributions = A.shape[1]
# loss matrix + normalization
M = ot.utils.dist0(n)
M /= M.max()
#%% plot the distributions
pl.figure(1, figsize=(6.4, 3))
for i in range(n_distributions):
pl.plot(x, A[:, i])
pl.title('Distributions')
pl.tight_layout()
#%% barycenter computation
alpha = 0.5 # 0<=alpha<=1
weights = np.array([1 - alpha, alpha])
# l2bary
bary_l2 = A.dot(weights)
# wasserstein
reg = 1e-3
ot.tic()
bary_wass = ot.bregman.barycenter(A, M, reg, weights)
ot.toc()
ot.tic()
bary_wass2 = ot.lp.barycenter(A, M, weights, solver='interior-point', verbose=True)
ot.toc()
problems.append([A, [bary_l2, bary_wass, bary_wass2]])
pl.figure(2)
pl.clf()
pl.subplot(2, 1, 1)
for i in range(n_distributions):
pl.plot(x, A[:, i])
pl.title('Distributions')
pl.subplot(2, 1, 2)
pl.plot(x, bary_l2, 'r', label='l2')
pl.plot(x, bary_wass, 'g', label='Reg Wasserstein')
pl.plot(x, bary_wass2, 'b', label='LP Wasserstein')
pl.legend()
pl.title('Barycenters')
pl.tight_layout()
##############################################################################
# Final figure
# ------------
#
#%% plot
nbm = len(problems)
nbm2 = (nbm // 2)
pl.figure(2, (20, 6))
pl.clf()
for i in range(nbm):
A = problems[i][0]
bary_l2 = problems[i][1][0]
bary_wass = problems[i][1][1]
bary_wass2 = problems[i][1][2]
pl.subplot(2, nbm, 1 + i)
for j in range(n_distributions):
pl.plot(x, A[:, j])
if i == nbm2:
pl.title('Distributions')
pl.xticks(())
pl.yticks(())
pl.subplot(2, nbm, 1 + i + nbm)
pl.plot(x, bary_l2, 'r', label='L2 (Euclidean)')
pl.plot(x, bary_wass, 'g', label='Reg Wasserstein')
pl.plot(x, bary_wass2, 'b', label='LP Wasserstein')
if i == nbm - 1:
pl.legend()
if i == nbm2:
pl.title('Barycenters')
pl.xticks(())
pl.yticks(())
|
