robustness in gans and in black-box optimization · demonstrate much more diversity in generated...
TRANSCRIPT
![Page 1: Robustness in GANs and in Black-box Optimization · demonstrate much more diversity in generated samples compared to DCGAN. 20 G(z) random “noise” z real data x D(x),D(G(z)) •](https://reader036.vdocument.in/reader036/viewer/2022081607/5ed4605505beeb3a300884e7/html5/thumbnails/1.jpg)
Robustness in GANs and in Black-box Optimization
Stefanie JegelkaMIT CSAIL
joint work with Zhi Xu, Chengtao Li, Ilija Bogunovic, Jonathan Scarlett and Volkan Cevher
![Page 2: Robustness in GANs and in Black-box Optimization · demonstrate much more diversity in generated samples compared to DCGAN. 20 G(z) random “noise” z real data x D(x),D(G(z)) •](https://reader036.vdocument.in/reader036/viewer/2022081607/5ed4605505beeb3a300884e7/html5/thumbnails/2.jpg)
Robustness in ML
Robustness in GANs
Representational Power in Deep Learning
Robust Black-Box Optimization
One unit is enough!
Gaussian Process Regression
-3
-2
-1
0
1
2
3
-2 -1 0 1 2
y(x)
x
Figure: Examples include WiFi localization, C14 callibration curve.
Robust Optimization, Generalization,
Discrete & Nonconvex Optimization
Generator
Critic
“noise”
![Page 3: Robustness in GANs and in Black-box Optimization · demonstrate much more diversity in generated samples compared to DCGAN. 20 G(z) random “noise” z real data x D(x),D(G(z)) •](https://reader036.vdocument.in/reader036/viewer/2022081607/5ed4605505beeb3a300884e7/html5/thumbnails/3.jpg)
Generative Adversarial Networks
Generator
Discriminator
min
Gmax
DV (G,D)
Under review as a conference paper at ICLR 2018
(a) DCGAN, trained with BN (b) DCGAN, trained without BN
(c) DAN-S, trained without BN (d) DAN-2S, trained without BN
Figure 14: DCGAN, DAN-S and DAN-2S trained on CelebA dataset. Both DAN-S and DAN-2Sdemonstrate much more diversity in generated samples compared to DCGAN.
20
G(z)
random“noise”
z
real data
x
D(x), D(G(z))
• attack: with probability p<0.5, discriminator’s output is manipulated
• generator doesn’t know which feedback is honest
max
DV (G,D)
minG
V (G,A(D))
discriminator: generator:
![Page 4: Robustness in GANs and in Black-box Optimization · demonstrate much more diversity in generated samples compared to DCGAN. 20 G(z) random “noise” z real data x D(x),D(G(z)) •](https://reader036.vdocument.in/reader036/viewer/2022081607/5ed4605505beeb3a300884e7/html5/thumbnails/4.jpg)
Generative Adversarial Networks
Generator
Discriminator
Under review as a conference paper at ICLR 2018
(a) DCGAN, trained with BN (b) DCGAN, trained without BN
(c) DAN-S, trained without BN (d) DAN-2S, trained without BN
Figure 14: DCGAN, DAN-S and DAN-2S trained on CelebA dataset. Both DAN-S and DAN-2Sdemonstrate much more diversity in generated samples compared to DCGAN.
20
G(z)
random“noise”
z
real data
x
D(x), D(G(z))
• attack: with probability p<0.5, discriminator’s output is manipulated
• generator doesn’t know which feedback is honest
Theorem: If adversary does a simple sign flip, then standard GAN no longer learns the right distribution.
A(D(x)) =
(1�D(x) with probability p
D(x) otherwise.
![Page 5: Robustness in GANs and in Black-box Optimization · demonstrate much more diversity in generated samples compared to DCGAN. 20 G(z) random “noise” z real data x D(x),D(G(z)) •](https://reader036.vdocument.in/reader036/viewer/2022081607/5ed4605505beeb3a300884e7/html5/thumbnails/5.jpg)
What makes GANs more robust?Generator
Discriminator
random“noise”
z
x
min
Gmax
DV (G,D)
min
G
max
D
Ex⇠Pdata [f(D(x))] + E
z⇠Pz [f(1�D(G(z)))]
<latexit sha1_base64="4nw31n2Az8Y+3hkxcbT/GOnikGg=">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</latexit><latexit sha1_base64="4nw31n2Az8Y+3hkxcbT/GOnikGg=">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</latexit><latexit sha1_base64="4nw31n2Az8Y+3hkxcbT/GOnikGg=">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</latexit><latexit sha1_base64="4nw31n2Az8Y+3hkxcbT/GOnikGg=">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</latexit>
score for real data “inverse” score for fake data
1. Model properties: transformation function
If:• is strictly increasing and differentiable • symmetry: for then model is robust
f(a) = �f(1� a)<latexit sha1_base64="NCWBkO+loYvDvO6+wsYG+rYV6Iw=">AAAB9XicbVDLSgNBEOz1GeMr6tHLYBCSQ8KuCHoRgl48RjAPSNbQO5lNhsw+mJlVwpL/8OJBEa/+izf/xkmyB00saCiquunu8mLBlbbtb2tldW19YzO3ld/e2d3bLxwcNlWUSMoaNBKRbHuomOAha2iuBWvHkmHgCdbyRjdTv/XIpOJReK/HMXMDHITc5xS1kR78EpbJFan4JaeC5V6haFftGcgycTJShAz1XuGr249oErBQU4FKdRw71m6KUnMq2CTfTRSLkY5wwDqGhhgw5aazqyfk1Ch94kfSVKjJTP09kWKg1DjwTGeAeqgWvan4n9dJtH/ppjyME81COl/kJ4LoiEwjIH0uGdVibAhSyc2thA5RItUmqLwJwVl8eZk0z6qOXXXuzou16yyOHBzDCZTAgQuowS3UoQEUJDzDK7xZT9aL9W59zFtXrGzmCP7A+vwBB4eQPg==</latexit><latexit sha1_base64="NCWBkO+loYvDvO6+wsYG+rYV6Iw=">AAAB9XicbVDLSgNBEOz1GeMr6tHLYBCSQ8KuCHoRgl48RjAPSNbQO5lNhsw+mJlVwpL/8OJBEa/+izf/xkmyB00saCiquunu8mLBlbbtb2tldW19YzO3ld/e2d3bLxwcNlWUSMoaNBKRbHuomOAha2iuBWvHkmHgCdbyRjdTv/XIpOJReK/HMXMDHITc5xS1kR78EpbJFan4JaeC5V6haFftGcgycTJShAz1XuGr249oErBQU4FKdRw71m6KUnMq2CTfTRSLkY5wwDqGhhgw5aazqyfk1Ch94kfSVKjJTP09kWKg1DjwTGeAeqgWvan4n9dJtH/ppjyME81COl/kJ4LoiEwjIH0uGdVibAhSyc2thA5RItUmqLwJwVl8eZk0z6qOXXXuzou16yyOHBzDCZTAgQuowS3UoQEUJDzDK7xZT9aL9W59zFtXrGzmCP7A+vwBB4eQPg==</latexit><latexit sha1_base64="NCWBkO+loYvDvO6+wsYG+rYV6Iw=">AAAB9XicbVDLSgNBEOz1GeMr6tHLYBCSQ8KuCHoRgl48RjAPSNbQO5lNhsw+mJlVwpL/8OJBEa/+izf/xkmyB00saCiquunu8mLBlbbtb2tldW19YzO3ld/e2d3bLxwcNlWUSMoaNBKRbHuomOAha2iuBWvHkmHgCdbyRjdTv/XIpOJReK/HMXMDHITc5xS1kR78EpbJFan4JaeC5V6haFftGcgycTJShAz1XuGr249oErBQU4FKdRw71m6KUnMq2CTfTRSLkY5wwDqGhhgw5aazqyfk1Ch94kfSVKjJTP09kWKg1DjwTGeAeqgWvan4n9dJtH/ppjyME81COl/kJ4LoiEwjIH0uGdVibAhSyc2thA5RItUmqLwJwVl8eZk0z6qOXXXuzou16yyOHBzDCZTAgQuowS3UoQEUJDzDK7xZT9aL9W59zFtXrGzmCP7A+vwBB4eQPg==</latexit><latexit sha1_base64="NCWBkO+loYvDvO6+wsYG+rYV6Iw=">AAAB9XicbVDLSgNBEOz1GeMr6tHLYBCSQ8KuCHoRgl48RjAPSNbQO5lNhsw+mJlVwpL/8OJBEa/+izf/xkmyB00saCiquunu8mLBlbbtb2tldW19YzO3ld/e2d3bLxwcNlWUSMoaNBKRbHuomOAha2iuBWvHkmHgCdbyRjdTv/XIpOJReK/HMXMDHITc5xS1kR78EpbJFan4JaeC5V6haFftGcgycTJShAz1XuGr249oErBQU4FKdRw71m6KUnMq2CTfTRSLkY5wwDqGhhgw5aazqyfk1Ch94kfSVKjJTP09kWKg1DjwTGeAeqgWvan4n9dJtH/ppjyME81COl/kJ4LoiEwjIH0uGdVibAhSyc2thA5RItUmqLwJwVl8eZk0z6qOXXXuzou16yyOHBzDCZTAgQuowS3UoQEUJDzDK7xZT9aL9W59zFtXrGzmCP7A+vwBB4eQPg==</latexit>
a 2 [0, 1]<latexit sha1_base64="vrLdIUQl/+8iK1k9MGH6/+Tgi6I=">AAAB8XicbVBNS8NAEJ3Ur1q/qh69LBbBg5REBD0WvXisYGsxDWWznbRLN5uwuxFK6L/w4kERr/4bb/4bt20O2vpg4PHeDDPzwlRwbVz32ymtrK6tb5Q3K1vbO7t71f2Dtk4yxbDFEpGoTkg1Ci6xZbgR2EkV0jgU+BCObqb+wxMqzRN5b8YpBjEdSB5xRo2VHmmXS+K7Z17Qq9bcujsDWSZeQWpQoNmrfnX7CctilIYJqrXvuakJcqoMZwInlW6mMaVsRAfoWyppjDrIZxdPyIlV+iRKlC1pyEz9PZHTWOtxHNrOmJqhXvSm4n+en5noKsi5TDODks0XRZkgJiHT90mfK2RGjC2hTHF7K2FDqigzNqSKDcFbfHmZtM/rnlv37i5qjesijjIcwTGcggeX0IBbaEILGEh4hld4c7Tz4rw7H/PWklPMHMIfOJ8/DUSP1w==</latexit><latexit sha1_base64="vrLdIUQl/+8iK1k9MGH6/+Tgi6I=">AAAB8XicbVBNS8NAEJ3Ur1q/qh69LBbBg5REBD0WvXisYGsxDWWznbRLN5uwuxFK6L/w4kERr/4bb/4bt20O2vpg4PHeDDPzwlRwbVz32ymtrK6tb5Q3K1vbO7t71f2Dtk4yxbDFEpGoTkg1Ci6xZbgR2EkV0jgU+BCObqb+wxMqzRN5b8YpBjEdSB5xRo2VHmmXS+K7Z17Qq9bcujsDWSZeQWpQoNmrfnX7CctilIYJqrXvuakJcqoMZwInlW6mMaVsRAfoWyppjDrIZxdPyIlV+iRKlC1pyEz9PZHTWOtxHNrOmJqhXvSm4n+en5noKsi5TDODks0XRZkgJiHT90mfK2RGjC2hTHF7K2FDqigzNqSKDcFbfHmZtM/rnlv37i5qjesijjIcwTGcggeX0IBbaEILGEh4hld4c7Tz4rw7H/PWklPMHMIfOJ8/DUSP1w==</latexit><latexit sha1_base64="vrLdIUQl/+8iK1k9MGH6/+Tgi6I=">AAAB8XicbVBNS8NAEJ3Ur1q/qh69LBbBg5REBD0WvXisYGsxDWWznbRLN5uwuxFK6L/w4kERr/4bb/4bt20O2vpg4PHeDDPzwlRwbVz32ymtrK6tb5Q3K1vbO7t71f2Dtk4yxbDFEpGoTkg1Ci6xZbgR2EkV0jgU+BCObqb+wxMqzRN5b8YpBjEdSB5xRo2VHmmXS+K7Z17Qq9bcujsDWSZeQWpQoNmrfnX7CctilIYJqrXvuakJcqoMZwInlW6mMaVsRAfoWyppjDrIZxdPyIlV+iRKlC1pyEz9PZHTWOtxHNrOmJqhXvSm4n+en5noKsi5TDODks0XRZkgJiHT90mfK2RGjC2hTHF7K2FDqigzNqSKDcFbfHmZtM/rnlv37i5qjesijjIcwTGcggeX0IBbaEILGEh4hld4c7Tz4rw7H/PWklPMHMIfOJ8/DUSP1w==</latexit><latexit sha1_base64="vrLdIUQl/+8iK1k9MGH6/+Tgi6I=">AAAB8XicbVBNS8NAEJ3Ur1q/qh69LBbBg5REBD0WvXisYGsxDWWznbRLN5uwuxFK6L/w4kERr/4bb/4bt20O2vpg4PHeDDPzwlRwbVz32ymtrK6tb5Q3K1vbO7t71f2Dtk4yxbDFEpGoTkg1Ci6xZbgR2EkV0jgU+BCObqb+wxMqzRN5b8YpBjEdSB5xRo2VHmmXS+K7Z17Qq9bcujsDWSZeQWpQoNmrfnX7CctilIYJqrXvuakJcqoMZwInlW6mMaVsRAfoWyppjDrIZxdPyIlV+iRKlC1pyEz9PZHTWOtxHNrOmJqhXvSm4n+en5noKsi5TDODks0XRZkgJiHT90mfK2RGjC2hTHF7K2FDqigzNqSKDcFbfHmZtM/rnlv37i5qjesijjIcwTGcggeX0IBbaEILGEh4hld4c7Tz4rw7H/PWklPMHMIfOJ8/DUSP1w==</latexit>
f<latexit sha1_base64="b4HLEbhr7TEtaehBb4ygFYyuiV8=">AAAB6HicbVBNS8NAEJ3Ur1q/qh69LBbBU0lEqMeiF48t2A9oQ9lsJ+3azSbsboQS+gu8eFDEqz/Jm//GbZuDtj4YeLw3w8y8IBFcG9f9dgobm1vbO8Xd0t7+weFR+fikreNUMWyxWMSqG1CNgktsGW4EdhOFNAoEdoLJ3dzvPKHSPJYPZpqgH9GR5CFn1FipGQ7KFbfqLkDWiZeTCuRoDMpf/WHM0gilYYJq3fPcxPgZVYYzgbNSP9WYUDahI+xZKmmE2s8Wh87IhVWGJIyVLWnIQv09kdFI62kU2M6ImrFe9ebif14vNeGNn3GZpAYlWy4KU0FMTOZfkyFXyIyYWkKZ4vZWwsZUUWZsNiUbgrf68jppX1U9t+o1ryv12zyOIpzBOVyCBzWowz00oAUMEJ7hFd6cR+fFeXc+lq0FJ585hT9wPn8AyvGM6g==</latexit><latexit sha1_base64="b4HLEbhr7TEtaehBb4ygFYyuiV8=">AAAB6HicbVBNS8NAEJ3Ur1q/qh69LBbBU0lEqMeiF48t2A9oQ9lsJ+3azSbsboQS+gu8eFDEqz/Jm//GbZuDtj4YeLw3w8y8IBFcG9f9dgobm1vbO8Xd0t7+weFR+fikreNUMWyxWMSqG1CNgktsGW4EdhOFNAoEdoLJ3dzvPKHSPJYPZpqgH9GR5CFn1FipGQ7KFbfqLkDWiZeTCuRoDMpf/WHM0gilYYJq3fPcxPgZVYYzgbNSP9WYUDahI+xZKmmE2s8Wh87IhVWGJIyVLWnIQv09kdFI62kU2M6ImrFe9ebif14vNeGNn3GZpAYlWy4KU0FMTOZfkyFXyIyYWkKZ4vZWwsZUUWZsNiUbgrf68jppX1U9t+o1ryv12zyOIpzBOVyCBzWowz00oAUMEJ7hFd6cR+fFeXc+lq0FJ585hT9wPn8AyvGM6g==</latexit><latexit sha1_base64="b4HLEbhr7TEtaehBb4ygFYyuiV8=">AAAB6HicbVBNS8NAEJ3Ur1q/qh69LBbBU0lEqMeiF48t2A9oQ9lsJ+3azSbsboQS+gu8eFDEqz/Jm//GbZuDtj4YeLw3w8y8IBFcG9f9dgobm1vbO8Xd0t7+weFR+fikreNUMWyxWMSqG1CNgktsGW4EdhOFNAoEdoLJ3dzvPKHSPJYPZpqgH9GR5CFn1FipGQ7KFbfqLkDWiZeTCuRoDMpf/WHM0gilYYJq3fPcxPgZVYYzgbNSP9WYUDahI+xZKmmE2s8Wh87IhVWGJIyVLWnIQv09kdFI62kU2M6ImrFe9ebif14vNeGNn3GZpAYlWy4KU0FMTOZfkyFXyIyYWkKZ4vZWwsZUUWZsNiUbgrf68jppX1U9t+o1ryv12zyOIpzBOVyCBzWowz00oAUMEJ7hFd6cR+fFeXc+lq0FJ585hT9wPn8AyvGM6g==</latexit><latexit sha1_base64="b4HLEbhr7TEtaehBb4ygFYyuiV8=">AAAB6HicbVBNS8NAEJ3Ur1q/qh69LBbBU0lEqMeiF48t2A9oQ9lsJ+3azSbsboQS+gu8eFDEqz/Jm//GbZuDtj4YeLw3w8y8IBFcG9f9dgobm1vbO8Xd0t7+weFR+fikreNUMWyxWMSqG1CNgktsGW4EdhOFNAoEdoLJ3dzvPKHSPJYPZpqgH9GR5CFn1FipGQ7KFbfqLkDWiZeTCuRoDMpf/WHM0gilYYJq3fPcxPgZVYYzgbNSP9WYUDahI+xZKmmE2s8Wh87IhVWGJIyVLWnIQv09kdFI62kU2M6ImrFe9ebif14vNeGNn3GZpAYlWy4KU0FMTOZfkyFXyIyYWkKZ4vZWwsZUUWZsNiUbgrf68jppX1U9t+o1ryv12zyOIpzBOVyCBzWowz00oAUMEJ7hFd6cR+fFeXc+lq0FJ585hT9wPn8AyvGM6g==</latexit>
![Page 6: Robustness in GANs and in Black-box Optimization · demonstrate much more diversity in generated samples compared to DCGAN. 20 G(z) random “noise” z real data x D(x),D(G(z)) •](https://reader036.vdocument.in/reader036/viewer/2022081607/5ed4605505beeb3a300884e7/html5/thumbnails/6.jpg)
What makes GANs more robust?Generator
Discriminator
random“noise”
z
x
min
Gmax
DV (G,D)
1. Model properties: symmetric transformation function
2. Training Algorithm: weight clipping (regularization) helps robustness
Generalization includes Wasserstein GANs!
![Page 7: Robustness in GANs and in Black-box Optimization · demonstrate much more diversity in generated samples compared to DCGAN. 20 G(z) random “noise” z real data x D(x),D(G(z)) •](https://reader036.vdocument.in/reader036/viewer/2022081607/5ed4605505beeb3a300884e7/html5/thumbnails/7.jpg)
Empirical Results• MNIST
D with a maximum absolute value of 0.1. Here, we apply the simple flipping adversary (2.2) with237
different error probabilities p. Figure 3 shows some typical results for one of the robust models and238
GAN, for p = 0 and p = 0.4. Indeed, as opposed to the GAN, the robust GAN reliably learns all239
modes, even with a fairly high p = 0.4. The figure illustrates an additional intuition: with higher240
noise p, learning indeed becomes more challenging, and the generator needs more iterations to learn.241
Figure 10 in the appendix confirms that this is generally the case.242
Clipping and its interaction with the model. To probe the effect of regularization, we next vary243
the clipping threshold. Figure 4 shows the success rate for different clipping thresholds, averaged244
over 10 runs. Here, a success is defined as correctly learning all the 8 modes (average number of245
modes are shown in the appendix). To better visualize the effect of clipping, D is intentionally made246
more powerful by having significantly more hidden neurons (4x more hidden neurons for each layer).247
0
0.2
0.4
0.6
0.8
1
1.2
None 1 0.5 0.1 0.05 0.01
Error Probability = 0
Gan Linear Tanh Erf Piece Piece2
0
0.2
0.4
0.6
0.8
1
1.2
None 1 0.5 0.1 0.05 0.01
Error Probability = 0.2
Gan Linear Tanh Erf Piece Piece2
0
0.2
0.4
0.6
0.8
1
1.2
None 1 0.5 0.1 0.05 0.01
Error Probability = 0.4
Gan Linear Tanh Erf Piece Piece2
SuccessRate
0
1
2
3
4
5
6
7
8
9
None 1 0.5 0.1 0.05 0.01
Error Probability = 0Gan Linear Tanh Erf Piece Piece2
0
1
2
3
4
5
6
7
8
9
None 1 0.5 0.1 0.05 0.01
Average # of Modes, Error = 0.2Gan Linear Tanh Erf Piece Piece2
0
1
2
3
4
5
6
7
8
9
None 1 0.5 0.1 0.05 0.01
Average # of Modes, Error = 0.4Gan Linear Tanh Erf Piece Piece2
Average#ofModes
Clipping
Error Probability = 0 Error Probability = 0.2 Error Probability = 0.4
0
0.2
0.4
0.6
0.8
1
1.2
None 1 0.5 0.1 0.05 0.01
Error Probability = 0Gan Linear Tanh Erf Piece Piece2
0
0.2
0.4
0.6
0.8
1
1.2
None 1 0.5 0.1 0.05 0.01
Error Probability = 0.2Gan Linear Tanh Erf Piece Piece2
0
0.2
0.4
0.6
0.8
1
1.2
None 1 0.5 0.1 0.05 0.01
Error Probability = 0.4Gan Linear Tanh Erf Piece Piece2
Clipping
Figure 4: Success rates and average number of learned modes for various models and clipping values.
Figure 4 offers several observations: (1) The training algorithm indeed affects the results. A too248
powerful disriminator (small threshold) generally impairs learning [2, 24]; very small thresholds limit249
the capacity of D too much. (2) However, consistently, if a robust GAN can learn the distribution250
without noise (p = 0), then it also learns the distribution with noise, confirming its robustness. In251
general, the robust GANs work across a wider range of clipping thresholds, i.e., are less sensitive to252
parameter choice of clipping. These observations support our theoretical analysis in Sections 2 and 4.253
An interesting phenomenon to note is that in some cases, clipping may increase the empirical254
robustness of the standard GAN, although it is still more sensitive than the robust models (threshold255
0.05 and p = 0.4). This phenomenon is orthogonal to our theoretical results; here, the algorithm256
aids empirical stability. It points to the important role of training algorithms in practice, a line of257
research underlying recent state-of-the-art results [32, 16, 38, 24]. In the next section we will see that,258
while clipping may help robustness, the GAN is still more brittle also towards the choice of algorithm259
(amount of regularization). Extending the theory to include both aspects, model and algorithm, is an260
interesting avenue of future research.261
5.3 MNIST262
GAN
Piece_GAN
Error Probability = 0 Error Probability = 0.3 Error Probability = 0 Error Probability = 0.3
Figure 5: Example results on MNIST (no clipping).
Next, we perform a similar analysis with the MNIST data, using a CNN for both G and D. Without263
clipping, both the GAN and the robust GANs learn the distribution well, and generate all digits with264
the same probability. Here, we call a learning experiment a success if G learns to generate all digits265
with the same probability (see the appendix for a plot of the total variation distance between the266
distribution of the learned digits and the uniform distribution). To further explore our theoretical267
frameworks, we apply a more sophisticated adversary as follows: �(D(x)) equals 1 � D(x) or268p
D(x) or D(x)
2, each with probability 0.1, and otherwise, �(D(x)) = D(x) (i.e., honest feedback269
with probability 0.7). By Theorem 6, all the robust models we explore here should be robust against270
7
GAN
D with a maximum absolute value of 0.1. Here, we apply the simple flipping adversary (2.2) with237
different error probabilities p. Figure 3 shows some typical results for one of the robust models and238
GAN, for p = 0 and p = 0.4. Indeed, as opposed to the GAN, the robust GAN reliably learns all239
modes, even with a fairly high p = 0.4. The figure illustrates an additional intuition: with higher240
noise p, learning indeed becomes more challenging, and the generator needs more iterations to learn.241
Figure 10 in the appendix confirms that this is generally the case.242
Clipping and its interaction with the model. To probe the effect of regularization, we next vary243
the clipping threshold. Figure 4 shows the success rate for different clipping thresholds, averaged244
over 10 runs. Here, a success is defined as correctly learning all the 8 modes (average number of245
modes are shown in the appendix). To better visualize the effect of clipping, D is intentionally made246
more powerful by having significantly more hidden neurons (4x more hidden neurons for each layer).247
0
0.2
0.4
0.6
0.8
1
1.2
None 1 0.5 0.1 0.05 0.01
Error Probability = 0
Gan Linear Tanh Erf Piece Piece2
0
0.2
0.4
0.6
0.8
1
1.2
None 1 0.5 0.1 0.05 0.01
Error Probability = 0.2
Gan Linear Tanh Erf Piece Piece2
0
0.2
0.4
0.6
0.8
1
1.2
None 1 0.5 0.1 0.05 0.01
Error Probability = 0.4
Gan Linear Tanh Erf Piece Piece2
SuccessRate
0
1
2
3
4
5
6
7
8
9
None 1 0.5 0.1 0.05 0.01
Error Probability = 0Gan Linear Tanh Erf Piece Piece2
0
1
2
3
4
5
6
7
8
9
None 1 0.5 0.1 0.05 0.01
Average # of Modes, Error = 0.2Gan Linear Tanh Erf Piece Piece2
0
1
2
3
4
5
6
7
8
9
None 1 0.5 0.1 0.05 0.01
Average # of Modes, Error = 0.4Gan Linear Tanh Erf Piece Piece2
Average#ofModes
Clipping
Error Probability = 0 Error Probability = 0.2 Error Probability = 0.4
0
0.2
0.4
0.6
0.8
1
1.2
None 1 0.5 0.1 0.05 0.01
Error Probability = 0Gan Linear Tanh Erf Piece Piece2
0
0.2
0.4
0.6
0.8
1
1.2
None 1 0.5 0.1 0.05 0.01
Error Probability = 0.2Gan Linear Tanh Erf Piece Piece2
0
0.2
0.4
0.6
0.8
1
1.2
None 1 0.5 0.1 0.05 0.01
Error Probability = 0.4Gan Linear Tanh Erf Piece Piece2
Clipping
Figure 4: Success rates and average number of learned modes for various models and clipping values.
Figure 4 offers several observations: (1) The training algorithm indeed affects the results. A too248
powerful disriminator (small threshold) generally impairs learning [2, 24]; very small thresholds limit249
the capacity of D too much. (2) However, consistently, if a robust GAN can learn the distribution250
without noise (p = 0), then it also learns the distribution with noise, confirming its robustness. In251
general, the robust GANs work across a wider range of clipping thresholds, i.e., are less sensitive to252
parameter choice of clipping. These observations support our theoretical analysis in Sections 2 and 4.253
An interesting phenomenon to note is that in some cases, clipping may increase the empirical254
robustness of the standard GAN, although it is still more sensitive than the robust models (threshold255
0.05 and p = 0.4). This phenomenon is orthogonal to our theoretical results; here, the algorithm256
aids empirical stability. It points to the important role of training algorithms in practice, a line of257
research underlying recent state-of-the-art results [32, 16, 38, 24]. In the next section we will see that,258
while clipping may help robustness, the GAN is still more brittle also towards the choice of algorithm259
(amount of regularization). Extending the theory to include both aspects, model and algorithm, is an260
interesting avenue of future research.261
5.3 MNIST262
GAN
Piece_GAN
Error Probability = 0 Error Probability = 0.3 Error Probability = 0 Error Probability = 0.3
Figure 5: Example results on MNIST (no clipping).
Next, we perform a similar analysis with the MNIST data, using a CNN for both G and D. Without263
clipping, both the GAN and the robust GANs learn the distribution well, and generate all digits with264
the same probability. Here, we call a learning experiment a success if G learns to generate all digits265
with the same probability (see the appendix for a plot of the total variation distance between the266
distribution of the learned digits and the uniform distribution). To further explore our theoretical267
frameworks, we apply a more sophisticated adversary as follows: �(D(x)) equals 1 � D(x) or268p
D(x) or D(x)
2, each with probability 0.1, and otherwise, �(D(x)) = D(x) (i.e., honest feedback269
with probability 0.7). By Theorem 6, all the robust models we explore here should be robust against270
7
stable GAN
![Page 8: Robustness in GANs and in Black-box Optimization · demonstrate much more diversity in generated samples compared to DCGAN. 20 G(z) random “noise” z real data x D(x),D(G(z)) •](https://reader036.vdocument.in/reader036/viewer/2022081607/5ed4605505beeb3a300884e7/html5/thumbnails/8.jpg)
Empirical Results
0
0.2
0.4
0.6
0.8
1
1.2
None 10 1 0.1 0.01 0.001
SuccessRate
Error Probability = 0GAN Linear Tanh Erf&Piece Piece2
0
0.2
0.4
0.6
0.8
1
1.2
None 10 1 0.1 0.01 0.001
Error Probability = 0.3GAN Linear Tanh Erf Piece Piece2
0.02
0.025
0.03
0.035
0.04
0.045
0.05
0.055
None 10 1 0.1 0.01 0.001
Error Probability = 0GAN Linear Tanh Erf Piece Piece2
0.02
0.025
0.03
0.035
0.04
0.045
0.05
0.055
None 10 1 0.1 0.01 0.001
Error Probability = 0.3
GAN Linear Tanh Erf Piece Piece2
TVDistancetothe
UniformDistribution
Clipping
Error probability = 0.3
Succ
ess
Rate
no clipping strict clipping
100% success
100% failure
GAN
stable GANs
• Weight Clipping (Regularization) helps robustness• Stable GANs are more robust to clipping threshold
![Page 9: Robustness in GANs and in Black-box Optimization · demonstrate much more diversity in generated samples compared to DCGAN. 20 G(z) random “noise” z real data x D(x),D(G(z)) •](https://reader036.vdocument.in/reader036/viewer/2022081607/5ed4605505beeb3a300884e7/html5/thumbnails/9.jpg)
Black-Box Optimization
f(x)
Goal: optimize a complex function
that is only accessible via expensive queries
2 Automatic Gait Optimization
Figure 1: The bio-inspired dynamicalbipedal walker Fox used for the exper-imental evaluation.
The search for appropriate parameters of a controller canbe formulated as an optimization problem, such as the min-imization
minimize✓2RD
f (✓) (1)
of an objective function f (·) with respect to the parame-ters ✓. In the context of gait optimization, this optimizationproblem is characterized as a global optimization of a zero-order stochastic objective function. Therefore, the use ofBayesian optimization well suits this challenging optimiza-tion task.
Bayesian Optimization Bayesian optimization is an iter-ative model-based global optimization method [7, 5, 11, 1].In Bayesian optimization, for each iteration (i.e., evalua-tion of the objective function f ), a GP model ✓ 7! f (✓)is learned from the data set T = {✓, f (✓)} composedby the past parameters ✓ and the corresponding measure-ments f (✓) of the objective function. This model is usedto predict the response surface ˆf and the corresponding ac-quisition surface ↵ (✓)1, once the response surface ˆf (·) is mapped through the acquisition func-tion ↵ (·). Using a global optimizer, the minimum ✓⇤ of the acquisition surface ↵ (✓) is computedwithout any evaluation of the objective function, e.g., no robot interaction. The current minimum ✓⇤
is evaluated on the robot and, together with the resulting measurement f (✓⇤), added to the datasetT.
Gaussian Process Model for Objective Function To create the model that maps ✓ 7! f(✓), wemake use of Bayesian non-parametric Gaussian Process regression [12]. Such a GP is a distributionover functions
f(✓) ⇠ GP (mf , k(✓p,✓q)) , (2)fully defined by a prior mean mf and a covariance function k(✓p,✓q). As prior mean, we choosemf ⌘ 0, while the chosen covariance function k(✓p,✓q) is the squared exponential with automaticrelevance determination and Gaussian noise
k(✓p,✓q) = �2f exp(�1
2 (✓p�✓q)T⇤�1
(✓p�✓q))+�2w�pq (3)
with ⇤ = diag([l21, ..., l2D]). Here, li are the characteristic length-scales, �2
f is the variance ofthe latent function f(·) and �2
w the noise variance. A practical issue, for both GP modeling andBayesian optimization, is the choice of the hyperparameters of the GP model, such as the charac-teristic length-scales li, the variance of the latent function �2
f and the noise variance �2w. In gait
optimization, these hyperparameters are often fixed a priori [9]. There are suggestions [8] that fixingthe hyperparameters can considerably speed up the convergence of Bayesian optimization. However,manually choosing the value of the hyperparameters requires extensive expert knowledge about thesystem that we want to optimize, which is often an unrealistic assumption. An alternative commonapproach is to automatically select the hyper-parameters by optimizing with respect to the marginallikelihood [12].
Acquisition Function A number of acquisition functions ↵ (·) exist, such as Probability of Im-provement [7], Expected Improvement [10], Upper Confidence Bound [3] and Entropy-Based Im-provements [4]. Experimental results [4] suggest that Expected Improvement on specific familiesof artificial functions performs better on average than Probability of Improvement and Upper Con-fidence Bound. However, these results do not necessarily hold true for real-world problems suchas gait optimization, where the objective functions are more complex to model. Both Probabilityof improvement [9] and Expected Improvement [14] have been previously employed in gait opti-mization. In our experiments, we evaluate Probability of Improvement, Expected Improvement andUpper Confidence Bound.
1The correct notation would be ↵�f̂ (✓)
�, but we use ↵ (✓) for notational convenience.
2
![Page 10: Robustness in GANs and in Black-box Optimization · demonstrate much more diversity in generated samples compared to DCGAN. 20 G(z) random “noise” z real data x D(x),D(G(z)) •](https://reader036.vdocument.in/reader036/viewer/2022081607/5ed4605505beeb3a300884e7/html5/thumbnails/10.jpg)
Black-Box OptimizationSequential Optimization: build internal model of f(x)
In each time step:
• Select a query point x
• Observe (noisy) f(x)
• update model
often: Gaussian ProcessGaussian Process Regression
-3
-2
-1
0
1
2
3
-2 -1 0 1 2
y(x)
x
Figure: Examples include WiFi localization, C14 callibration curve.
select queries:uncertainty and expected function value, e.g. maximizing
ucb(x) = f̂(x) + �
1/2�(x)
<latexit sha1_base64="KmWnc+Dx1ykEeOMpOx11pR7+DNc=">AAACHXicbVBNSwMxFMzW7/pV9eglWARFqLuloBeh6MWjgrVCt5a3abYNTXaX5K1Ylv4RL/4VLx4U8eBF/DemtQdtHQhMZt4jmQkSKQy67peTm5mdm19YXMovr6yurRc2Nq9NnGrGayyWsb4JwHApIl5DgZLfJJqDCiSvB72zoV+/49qIOLrCfsKbCjqRCAUDtFKrUPEVYFerLGXBYO9+n55QvwuYhaPLAfUDjnCbeYflAfWN6CiweqtQdEvuCHSaeGNSJGNctAoffjtmqeIRMgnGNDw3wWYGGgWTfJD3U8MTYD3o8IalEShumtko3YDuWqVNw1jbEyEdqb83MlDG9FVgJ4dZzKQ3FP/zGimGx81MREmKPGI/D4WppBjTYVW0LTRnKPuWANPC/pWyLmhgaAvN2xK8ycjT5Lpc8iy/rBSrp+M6Fsk22SF7xCNHpErOyQWpEUYeyBN5Ia/Oo/PsvDnvP6M5Z7yzRf7A+fwGy62gcQ==</latexit><latexit sha1_base64="KmWnc+Dx1ykEeOMpOx11pR7+DNc=">AAACHXicbVBNSwMxFMzW7/pV9eglWARFqLuloBeh6MWjgrVCt5a3abYNTXaX5K1Ylv4RL/4VLx4U8eBF/DemtQdtHQhMZt4jmQkSKQy67peTm5mdm19YXMovr6yurRc2Nq9NnGrGayyWsb4JwHApIl5DgZLfJJqDCiSvB72zoV+/49qIOLrCfsKbCjqRCAUDtFKrUPEVYFerLGXBYO9+n55QvwuYhaPLAfUDjnCbeYflAfWN6CiweqtQdEvuCHSaeGNSJGNctAoffjtmqeIRMgnGNDw3wWYGGgWTfJD3U8MTYD3o8IalEShumtko3YDuWqVNw1jbEyEdqb83MlDG9FVgJ4dZzKQ3FP/zGimGx81MREmKPGI/D4WppBjTYVW0LTRnKPuWANPC/pWyLmhgaAvN2xK8ycjT5Lpc8iy/rBSrp+M6Fsk22SF7xCNHpErOyQWpEUYeyBN5Ia/Oo/PsvDnvP6M5Z7yzRf7A+fwGy62gcQ==</latexit><latexit sha1_base64="KmWnc+Dx1ykEeOMpOx11pR7+DNc=">AAACHXicbVBNSwMxFMzW7/pV9eglWARFqLuloBeh6MWjgrVCt5a3abYNTXaX5K1Ylv4RL/4VLx4U8eBF/DemtQdtHQhMZt4jmQkSKQy67peTm5mdm19YXMovr6yurRc2Nq9NnGrGayyWsb4JwHApIl5DgZLfJJqDCiSvB72zoV+/49qIOLrCfsKbCjqRCAUDtFKrUPEVYFerLGXBYO9+n55QvwuYhaPLAfUDjnCbeYflAfWN6CiweqtQdEvuCHSaeGNSJGNctAoffjtmqeIRMgnGNDw3wWYGGgWTfJD3U8MTYD3o8IalEShumtko3YDuWqVNw1jbEyEdqb83MlDG9FVgJ4dZzKQ3FP/zGimGx81MREmKPGI/D4WppBjTYVW0LTRnKPuWANPC/pWyLmhgaAvN2xK8ycjT5Lpc8iy/rBSrp+M6Fsk22SF7xCNHpErOyQWpEUYeyBN5Ia/Oo/PsvDnvP6M5Z7yzRf7A+fwGy62gcQ==</latexit><latexit sha1_base64="KmWnc+Dx1ykEeOMpOx11pR7+DNc=">AAACHXicbVBNSwMxFMzW7/pV9eglWARFqLuloBeh6MWjgrVCt5a3abYNTXaX5K1Ylv4RL/4VLx4U8eBF/DemtQdtHQhMZt4jmQkSKQy67peTm5mdm19YXMovr6yurRc2Nq9NnGrGayyWsb4JwHApIl5DgZLfJJqDCiSvB72zoV+/49qIOLrCfsKbCjqRCAUDtFKrUPEVYFerLGXBYO9+n55QvwuYhaPLAfUDjnCbeYflAfWN6CiweqtQdEvuCHSaeGNSJGNctAoffjtmqeIRMgnGNDw3wWYGGgWTfJD3U8MTYD3o8IalEShumtko3YDuWqVNw1jbEyEdqb83MlDG9FVgJ4dZzKQ3FP/zGimGx81MREmKPGI/D4WppBjTYVW0LTRnKPuWANPC/pWyLmhgaAvN2xK8ycjT5Lpc8iy/rBSrp+M6Fsk22SF7xCNHpErOyQWpEUYeyBN5Ia/Oo/PsvDnvP6M5Z7yzRf7A+fwGy62gcQ==</latexit>
![Page 11: Robustness in GANs and in Black-box Optimization · demonstrate much more diversity in generated samples compared to DCGAN. 20 G(z) random “noise” z real data x D(x),D(G(z)) •](https://reader036.vdocument.in/reader036/viewer/2022081607/5ed4605505beeb3a300884e7/html5/thumbnails/11.jpg)
Robust Optimization with GPsObserved f(x) may be (adversarially) perturbed:
• Robotics: simulations vs. real data
• Parameter tuning: estimation with limited data
• Time-varying functions
min�2�✏(x)
f(x+ �)
Δϵ(x) = {x′�− x : x′� ∈ D and d(x, x′�) ≤ ϵ}
maxx∈D
minδ∈Δϵ(x)
f(x + δ)Problem:
standard methods can fail!
suboptimal decision!
![Page 12: Robustness in GANs and in Black-box Optimization · demonstrate much more diversity in generated samples compared to DCGAN. 20 G(z) random “noise” z real data x D(x),D(G(z)) •](https://reader036.vdocument.in/reader036/viewer/2022081607/5ed4605505beeb3a300884e7/html5/thumbnails/12.jpg)
O*( 1η2 (log 1
η )2p) ⌘<latexit sha1_base64="pS+PZ/UV6ooP4GI+75b54U/Pe1c=">AAAB63icbZBNSwMxEIZn61etX1WPXoJF8FR2RdBj0YvHCrYW2qVk02wbmmSXZFYoS/+CFw+KePUPefPfmLZ70NYXAg/vzJCZN0qlsOj7315pbX1jc6u8XdnZ3ds/qB4etW2SGcZbLJGJ6UTUcik0b6FAyTup4VRFkj9G49tZ/fGJGysS/YCTlIeKDrWIBaM4s3ocab9a8+v+XGQVggJqUKjZr371BgnLFNfIJLW2G/gphjk1KJjk00ovszylbEyHvOtQU8VtmM93nZIz5wxInBj3NJK5+3sip8raiYpcp6I4ssu1mflfrZthfB3mQqcZcs0WH8WZJJiQ2eFkIAxnKCcOKDPC7UrYiBrK0MVTcSEEyyevQvuiHji+v6w1boo4ynACp3AOAVxBA+6gCS1gMIJneIU3T3kv3rv3sWgtecXMMfyR9/kDCOSOOA==</latexit><latexit sha1_base64="pS+PZ/UV6ooP4GI+75b54U/Pe1c=">AAAB63icbZBNSwMxEIZn61etX1WPXoJF8FR2RdBj0YvHCrYW2qVk02wbmmSXZFYoS/+CFw+KePUPefPfmLZ70NYXAg/vzJCZN0qlsOj7315pbX1jc6u8XdnZ3ds/qB4etW2SGcZbLJGJ6UTUcik0b6FAyTup4VRFkj9G49tZ/fGJGysS/YCTlIeKDrWIBaM4s3ocab9a8+v+XGQVggJqUKjZr371BgnLFNfIJLW2G/gphjk1KJjk00ovszylbEyHvOtQU8VtmM93nZIz5wxInBj3NJK5+3sip8raiYpcp6I4ssu1mflfrZthfB3mQqcZcs0WH8WZJJiQ2eFkIAxnKCcOKDPC7UrYiBrK0MVTcSEEyyevQvuiHji+v6w1boo4ynACp3AOAVxBA+6gCS1gMIJneIU3T3kv3rv3sWgtecXMMfyR9/kDCOSOOA==</latexit><latexit sha1_base64="pS+PZ/UV6ooP4GI+75b54U/Pe1c=">AAAB63icbZBNSwMxEIZn61etX1WPXoJF8FR2RdBj0YvHCrYW2qVk02wbmmSXZFYoS/+CFw+KePUPefPfmLZ70NYXAg/vzJCZN0qlsOj7315pbX1jc6u8XdnZ3ds/qB4etW2SGcZbLJGJ6UTUcik0b6FAyTup4VRFkj9G49tZ/fGJGysS/YCTlIeKDrWIBaM4s3ocab9a8+v+XGQVggJqUKjZr371BgnLFNfIJLW2G/gphjk1KJjk00ovszylbEyHvOtQU8VtmM93nZIz5wxInBj3NJK5+3sip8raiYpcp6I4ssu1mflfrZthfB3mQqcZcs0WH8WZJJiQ2eFkIAxnKCcOKDPC7UrYiBrK0MVTcSEEyyevQvuiHji+v6w1boo4ynACp3AOAVxBA+6gCS1gMIJneIU3T3kv3rv3sWgtecXMMfyR9/kDCOSOOA==</latexit><latexit sha1_base64="pS+PZ/UV6ooP4GI+75b54U/Pe1c=">AAAB63icbZBNSwMxEIZn61etX1WPXoJF8FR2RdBj0YvHCrYW2qVk02wbmmSXZFYoS/+CFw+KePUPefPfmLZ70NYXAg/vzJCZN0qlsOj7315pbX1jc6u8XdnZ3ds/qB4etW2SGcZbLJGJ6UTUcik0b6FAyTup4VRFkj9G49tZ/fGJGysS/YCTlIeKDrWIBaM4s3ocab9a8+v+XGQVggJqUKjZr371BgnLFNfIJLW2G/gphjk1KJjk00ovszylbEyHvOtQU8VtmM93nZIz5wxInBj3NJK5+3sip8raiYpcp6I4ssu1mflfrZthfB3mQqcZcs0WH8WZJJiQ2eFkIAxnKCcOKDPC7UrYiBrK0MVTcSEEyyevQvuiHji+v6w1boo4ynACp3AOAVxBA+6gCS1gMIJneIU3T3kv3rv3sWgtecXMMfyR9/kDCOSOOA==</latexit>
StableOpt AlgorithmIn every round:
• select
• select
• observe and update with
Theorem (RBF kernel): sample complexity:
steps for -suboptimality whp.
• closely matching lower bound
• algorithm generalizes to many other settings!
x̃t = argmaxx∈D
minδ∈Δϵ(x)
ucbt−1(x + δ)
δt = argminδ∈Δϵ(x̃t)
lcbt−1(x̃t + δ)
yt = f(x̃t+δt) + zt {(x̃t+δt, yt)}
upper confidence bound
lower confidence bound
Gaussian Process Regression
-3
-2
-1
0
1
2
3
-2 -1 0 1 2
y(x)
x
Figure: Examples include WiFi localization, C14 callibration curve.
![Page 13: Robustness in GANs and in Black-box Optimization · demonstrate much more diversity in generated samples compared to DCGAN. 20 G(z) random “noise” z real data x D(x),D(G(z)) •](https://reader036.vdocument.in/reader036/viewer/2022081607/5ed4605505beeb3a300884e7/html5/thumbnails/13.jpg)
VariationsRobustness to unknown parameters
• is smooth wrt input and parameters
Robust estimation
• estimate of true parameters
Robust group identification
• input space partitioned into groups group with highest worst-case value
maxx∈D
minθ∈Θ
f(x, θ)✓
<latexit sha1_base64="+3IVlR1SceYdoobQHFCnv6mzqcQ=">AAAB7XicbZBNSwMxEIZn61etX1WPXoJF8FR2RdBjxYvHCvYD2qVk07SNzSZLMiuUpf/BiwdFvPp/vPlvTNs9aOsLgYd3ZsjMGyVSWPT9b6+wtr6xuVXcLu3s7u0flA+PmlanhvEG01KbdkQtl0LxBgqUvJ0YTuNI8lY0vp3VW0/cWKHVA04SHsZ0qMRAMIrOanZxxJH2yhW/6s9FViHIoQK56r3yV7evWRpzhUxSazuBn2CYUYOCST4tdVPLE8rGdMg7DhWNuQ2z+bZTcuacPhlo455CMnd/T2Q0tnYSR64zpjiyy7WZ+V+tk+LgOsyESlLkii0+GqSSoCaz00lfGM5QThxQZoTblbARNZShC6jkQgiWT16F5kU1cHx/Wand5HEU4QRO4RwCuIIa3EEdGsDgEZ7hFd487b14797HorXg5TPH8Efe5w+jrI8n</latexit><latexit sha1_base64="+3IVlR1SceYdoobQHFCnv6mzqcQ=">AAAB7XicbZBNSwMxEIZn61etX1WPXoJF8FR2RdBjxYvHCvYD2qVk07SNzSZLMiuUpf/BiwdFvPp/vPlvTNs9aOsLgYd3ZsjMGyVSWPT9b6+wtr6xuVXcLu3s7u0flA+PmlanhvEG01KbdkQtl0LxBgqUvJ0YTuNI8lY0vp3VW0/cWKHVA04SHsZ0qMRAMIrOanZxxJH2yhW/6s9FViHIoQK56r3yV7evWRpzhUxSazuBn2CYUYOCST4tdVPLE8rGdMg7DhWNuQ2z+bZTcuacPhlo455CMnd/T2Q0tnYSR64zpjiyy7WZ+V+tk+LgOsyESlLkii0+GqSSoCaz00lfGM5QThxQZoTblbARNZShC6jkQgiWT16F5kU1cHx/Wand5HEU4QRO4RwCuIIa3EEdGsDgEZ7hFd487b14797HorXg5TPH8Efe5w+jrI8n</latexit><latexit sha1_base64="+3IVlR1SceYdoobQHFCnv6mzqcQ=">AAAB7XicbZBNSwMxEIZn61etX1WPXoJF8FR2RdBjxYvHCvYD2qVk07SNzSZLMiuUpf/BiwdFvPp/vPlvTNs9aOsLgYd3ZsjMGyVSWPT9b6+wtr6xuVXcLu3s7u0flA+PmlanhvEG01KbdkQtl0LxBgqUvJ0YTuNI8lY0vp3VW0/cWKHVA04SHsZ0qMRAMIrOanZxxJH2yhW/6s9FViHIoQK56r3yV7evWRpzhUxSazuBn2CYUYOCST4tdVPLE8rGdMg7DhWNuQ2z+bZTcuacPhlo455CMnd/T2Q0tnYSR64zpjiyy7WZ+V+tk+LgOsyESlLkii0+GqSSoCaz00lfGM5QThxQZoTblbARNZShC6jkQgiWT16F5kU1cHx/Wand5HEU4QRO4RwCuIIa3EEdGsDgEZ7hFd487b14797HorXg5TPH8Efe5w+jrI8n</latexit><latexit sha1_base64="+3IVlR1SceYdoobQHFCnv6mzqcQ=">AAAB7XicbZBNSwMxEIZn61etX1WPXoJF8FR2RdBjxYvHCvYD2qVk07SNzSZLMiuUpf/BiwdFvPp/vPlvTNs9aOsLgYd3ZsjMGyVSWPT9b6+wtr6xuVXcLu3s7u0flA+PmlanhvEG01KbdkQtl0LxBgqUvJ0YTuNI8lY0vp3VW0/cWKHVA04SHsZ0qMRAMIrOanZxxJH2yhW/6s9FViHIoQK56r3yV7evWRpzhUxSazuBn2CYUYOCST4tdVPLE8rGdMg7DhWNuQ2z+bZTcuacPhlo455CMnd/T2Q0tnYSR64zpjiyy7WZ+V+tk+LgOsyESlLkii0+GqSSoCaz00lfGM5QThxQZoTblbARNZShC6jkQgiWT16F5kU1cHx/Wand5HEU4QRO4RwCuIIa3EEdGsDgEZ7hFd487b14797HorXg5TPH8Efe5w+jrI8n</latexit>
x
<latexit sha1_base64="v11J2ieZIwbhGlKoKPnDtKPEUro=">AAAB6HicbZBNS8NAEIYn9avWr6pHL4tF8FQSEfRY8eKxBfsBbSib7aRdu9mE3Y1YQn+BFw+KePUnefPfuG1z0NYXFh7emWFn3iARXBvX/XYKa+sbm1vF7dLO7t7+QfnwqKXjVDFssljEqhNQjYJLbBpuBHYShTQKBLaD8e2s3n5EpXks780kQT+iQ8lDzqixVuOpX664VXcusgpeDhXIVe+Xv3qDmKURSsME1brruYnxM6oMZwKnpV6qMaFsTIfYtShphNrP5otOyZl1BiSMlX3SkLn7eyKjkdaTKLCdETUjvVybmf/VuqkJr/2MyyQ1KNniozAVxMRkdjUZcIXMiIkFyhS3uxI2oooyY7Mp2RC85ZNXoXVR9Sw3Liu1mzyOIpzAKZyDB1dQgzuoQxMYIDzDK7w5D86L8+58LFoLTj5zDH/kfP4A5e6M+w==</latexit><latexit sha1_base64="v11J2ieZIwbhGlKoKPnDtKPEUro=">AAAB6HicbZBNS8NAEIYn9avWr6pHL4tF8FQSEfRY8eKxBfsBbSib7aRdu9mE3Y1YQn+BFw+KePUnefPfuG1z0NYXFh7emWFn3iARXBvX/XYKa+sbm1vF7dLO7t7+QfnwqKXjVDFssljEqhNQjYJLbBpuBHYShTQKBLaD8e2s3n5EpXks780kQT+iQ8lDzqixVuOpX664VXcusgpeDhXIVe+Xv3qDmKURSsME1brruYnxM6oMZwKnpV6qMaFsTIfYtShphNrP5otOyZl1BiSMlX3SkLn7eyKjkdaTKLCdETUjvVybmf/VuqkJr/2MyyQ1KNniozAVxMRkdjUZcIXMiIkFyhS3uxI2oooyY7Mp2RC85ZNXoXVR9Sw3Liu1mzyOIpzAKZyDB1dQgzuoQxMYIDzDK7w5D86L8+58LFoLTj5zDH/kfP4A5e6M+w==</latexit><latexit sha1_base64="v11J2ieZIwbhGlKoKPnDtKPEUro=">AAAB6HicbZBNS8NAEIYn9avWr6pHL4tF8FQSEfRY8eKxBfsBbSib7aRdu9mE3Y1YQn+BFw+KePUnefPfuG1z0NYXFh7emWFn3iARXBvX/XYKa+sbm1vF7dLO7t7+QfnwqKXjVDFssljEqhNQjYJLbBpuBHYShTQKBLaD8e2s3n5EpXks780kQT+iQ8lDzqixVuOpX664VXcusgpeDhXIVe+Xv3qDmKURSsME1brruYnxM6oMZwKnpV6qMaFsTIfYtShphNrP5otOyZl1BiSMlX3SkLn7eyKjkdaTKLCdETUjvVybmf/VuqkJr/2MyyQ1KNniozAVxMRkdjUZcIXMiIkFyhS3uxI2oooyY7Mp2RC85ZNXoXVR9Sw3Liu1mzyOIpzAKZyDB1dQgzuoQxMYIDzDK7w5D86L8+58LFoLTj5zDH/kfP4A5e6M+w==</latexit><latexit sha1_base64="v11J2ieZIwbhGlKoKPnDtKPEUro=">AAAB6HicbZBNS8NAEIYn9avWr6pHL4tF8FQSEfRY8eKxBfsBbSib7aRdu9mE3Y1YQn+BFw+KePUnefPfuG1z0NYXFh7emWFn3iARXBvX/XYKa+sbm1vF7dLO7t7+QfnwqKXjVDFssljEqhNQjYJLbBpuBHYShTQKBLaD8e2s3n5EpXks780kQT+iQ8lDzqixVuOpX664VXcusgpeDhXIVe+Xv3qDmKURSsME1brruYnxM6oMZwKnpV6qMaFsTIfYtShphNrP5otOyZl1BiSMlX3SkLn7eyKjkdaTKLCdETUjvVybmf/VuqkJr/2MyyQ1KNniozAVxMRkdjUZcIXMiIkFyhS3uxI2oooyY7Mp2RC85ZNXoXVR9Sw3Liu1mzyOIpzAKZyDB1dQgzuoQxMYIDzDK7w5D86L8+58LFoLTj5zDH/kfP4A5e6M+w==</latexit>
f : D × Θ → ℝ
✓̄<latexit sha1_base64="jBreMVOm7KmUp2dV9Uzn1wdlXn0=">AAAB83icbZBNS8NAEIYn9avWr6pHL8EieCqJCHqsePFYwdZCE8pku22XbjZhdyKU0L/hxYMiXv0z3vw3btsctPWFhYd3ZpjZN0qlMOR5305pbX1jc6u8XdnZ3ds/qB4etU2SacZbLJGJ7kRouBSKt0iQ5J1Uc4wjyR+j8e2s/vjEtRGJeqBJysMYh0oMBEOyVhBEqPOARpxw2qvWvLo3l7sKfgE1KNTsVb+CfsKymCtiEo3p+l5KYY6aBJN8Wgkyw1NkYxzyrkWFMTdhPr956p5Zp+8OEm2fInfu/p7IMTZmEke2M0YameXazPyv1s1ocB3mQqUZccUWiwaZdClxZwG4faE5IzmxgEwLe6vLRqiRkY2pYkPwl7+8Cu2Lum/5/rLWuCniKMMJnMI5+HAFDbiDJrSAQQrP8ApvTua8OO/Ox6K15BQzx/BHzucPbd2R7A==</latexit><latexit sha1_base64="jBreMVOm7KmUp2dV9Uzn1wdlXn0=">AAAB83icbZBNS8NAEIYn9avWr6pHL8EieCqJCHqsePFYwdZCE8pku22XbjZhdyKU0L/hxYMiXv0z3vw3btsctPWFhYd3ZpjZN0qlMOR5305pbX1jc6u8XdnZ3ds/qB4etU2SacZbLJGJ7kRouBSKt0iQ5J1Uc4wjyR+j8e2s/vjEtRGJeqBJysMYh0oMBEOyVhBEqPOARpxw2qvWvLo3l7sKfgE1KNTsVb+CfsKymCtiEo3p+l5KYY6aBJN8Wgkyw1NkYxzyrkWFMTdhPr956p5Zp+8OEm2fInfu/p7IMTZmEke2M0YameXazPyv1s1ocB3mQqUZccUWiwaZdClxZwG4faE5IzmxgEwLe6vLRqiRkY2pYkPwl7+8Cu2Lum/5/rLWuCniKMMJnMI5+HAFDbiDJrSAQQrP8ApvTua8OO/Ox6K15BQzx/BHzucPbd2R7A==</latexit><latexit sha1_base64="jBreMVOm7KmUp2dV9Uzn1wdlXn0=">AAAB83icbZBNS8NAEIYn9avWr6pHL8EieCqJCHqsePFYwdZCE8pku22XbjZhdyKU0L/hxYMiXv0z3vw3btsctPWFhYd3ZpjZN0qlMOR5305pbX1jc6u8XdnZ3ds/qB4etU2SacZbLJGJ7kRouBSKt0iQ5J1Uc4wjyR+j8e2s/vjEtRGJeqBJysMYh0oMBEOyVhBEqPOARpxw2qvWvLo3l7sKfgE1KNTsVb+CfsKymCtiEo3p+l5KYY6aBJN8Wgkyw1NkYxzyrkWFMTdhPr956p5Zp+8OEm2fInfu/p7IMTZmEke2M0YameXazPyv1s1ocB3mQqUZccUWiwaZdClxZwG4faE5IzmxgEwLe6vLRqiRkY2pYkPwl7+8Cu2Lum/5/rLWuCniKMMJnMI5+HAFDbiDJrSAQQrP8ApvTua8OO/Ox6K15BQzx/BHzucPbd2R7A==</latexit><latexit sha1_base64="jBreMVOm7KmUp2dV9Uzn1wdlXn0=">AAAB83icbZBNS8NAEIYn9avWr6pHL8EieCqJCHqsePFYwdZCE8pku22XbjZhdyKU0L/hxYMiXv0z3vw3btsctPWFhYd3ZpjZN0qlMOR5305pbX1jc6u8XdnZ3ds/qB4etU2SacZbLJGJ7kRouBSKt0iQ5J1Uc4wjyR+j8e2s/vjEtRGJeqBJysMYh0oMBEOyVhBEqPOARpxw2qvWvLo3l7sKfgE1KNTsVb+CfsKymCtiEo3p+l5KYY6aBJN8Wgkyw1NkYxzyrkWFMTdhPr956p5Zp+8OEm2fInfu/p7IMTZmEke2M0YameXazPyv1s1ocB3mQqUZccUWiwaZdClxZwG4faE5IzmxgEwLe6vLRqiRkY2pYkPwl7+8Cu2Lum/5/rLWuCniKMMJnMI5+HAFDbiDJrSAQQrP8ApvTua8OO/Ox6K15BQzx/BHzucPbd2R7A==</latexit>
✓⇤ 2 ⇥<latexit sha1_base64="cto74bMvj9LZ8Cp+ym/6Bd9imSQ=">AAAB/HicbZDLSsNAFIYn9VbrLdqlm8EiiIuSiKDLihuXFXqDJpbJdNoOnUzCzIkQQn0VNy4UceuDuPNtnLRZaOsPA9/85xzmzB/EgmtwnG+rtLa+sblV3q7s7O7tH9iHRx0dJYqyNo1EpHoB0UxwydrAQbBerBgJA8G6wfQ2r3cfmdI8ki1IY+aHZCz5iFMCxhrYVQ8mDMjDOfa4xF4rvwzsmlN35sKr4BZQQ4WaA/vLG0Y0CZkEKojWfdeJwc+IAk4Fm1W8RLOY0CkZs75BSUKm/Wy+/AyfGmeIR5EyRwKeu78nMhJqnYaB6QwJTPRyLTf/q/UTGF37GZdxAkzSxUOjRGCIcJ4EHnLFKIjUAKGKm10xnRBFKJi8KiYEd/nLq9C5qLuG7y9rjZsijjI6RifoDLnoCjXQHWqiNqIoRc/oFb1ZT9aL9W59LFpLVjFTRX9kff4AuOKUJw==</latexit><latexit sha1_base64="cto74bMvj9LZ8Cp+ym/6Bd9imSQ=">AAAB/HicbZDLSsNAFIYn9VbrLdqlm8EiiIuSiKDLihuXFXqDJpbJdNoOnUzCzIkQQn0VNy4UceuDuPNtnLRZaOsPA9/85xzmzB/EgmtwnG+rtLa+sblV3q7s7O7tH9iHRx0dJYqyNo1EpHoB0UxwydrAQbBerBgJA8G6wfQ2r3cfmdI8ki1IY+aHZCz5iFMCxhrYVQ8mDMjDOfa4xF4rvwzsmlN35sKr4BZQQ4WaA/vLG0Y0CZkEKojWfdeJwc+IAk4Fm1W8RLOY0CkZs75BSUKm/Wy+/AyfGmeIR5EyRwKeu78nMhJqnYaB6QwJTPRyLTf/q/UTGF37GZdxAkzSxUOjRGCIcJ4EHnLFKIjUAKGKm10xnRBFKJi8KiYEd/nLq9C5qLuG7y9rjZsijjI6RifoDLnoCjXQHWqiNqIoRc/oFb1ZT9aL9W59LFpLVjFTRX9kff4AuOKUJw==</latexit><latexit sha1_base64="cto74bMvj9LZ8Cp+ym/6Bd9imSQ=">AAAB/HicbZDLSsNAFIYn9VbrLdqlm8EiiIuSiKDLihuXFXqDJpbJdNoOnUzCzIkQQn0VNy4UceuDuPNtnLRZaOsPA9/85xzmzB/EgmtwnG+rtLa+sblV3q7s7O7tH9iHRx0dJYqyNo1EpHoB0UxwydrAQbBerBgJA8G6wfQ2r3cfmdI8ki1IY+aHZCz5iFMCxhrYVQ8mDMjDOfa4xF4rvwzsmlN35sKr4BZQQ4WaA/vLG0Y0CZkEKojWfdeJwc+IAk4Fm1W8RLOY0CkZs75BSUKm/Wy+/AyfGmeIR5EyRwKeu78nMhJqnYaB6QwJTPRyLTf/q/UTGF37GZdxAkzSxUOjRGCIcJ4EHnLFKIjUAKGKm10xnRBFKJi8KiYEd/nLq9C5qLuG7y9rjZsijjI6RifoDLnoCjXQHWqiNqIoRc/oFb1ZT9aL9W59LFpLVjFTRX9kff4AuOKUJw==</latexit><latexit sha1_base64="cto74bMvj9LZ8Cp+ym/6Bd9imSQ=">AAAB/HicbZDLSsNAFIYn9VbrLdqlm8EiiIuSiKDLihuXFXqDJpbJdNoOnUzCzIkQQn0VNy4UceuDuPNtnLRZaOsPA9/85xzmzB/EgmtwnG+rtLa+sblV3q7s7O7tH9iHRx0dJYqyNo1EpHoB0UxwydrAQbBerBgJA8G6wfQ2r3cfmdI8ki1IY+aHZCz5iFMCxhrYVQ8mDMjDOfa4xF4rvwzsmlN35sKr4BZQQ4WaA/vLG0Y0CZkEKojWfdeJwc+IAk4Fm1W8RLOY0CkZs75BSUKm/Wy+/AyfGmeIR5EyRwKeu78nMhJqnYaB6QwJTPRyLTf/q/UTGF37GZdxAkzSxUOjRGCIcJ4EHnLFKIjUAKGKm10xnRBFKJi8KiYEd/nLq9C5qLuG7y9rjZsijjI6RifoDLnoCjXQHWqiNqIoRc/oFb1ZT9aL9W59LFpLVjFTRX9kff4AuOKUJw==</latexit>
maxx∈D
minδθ∈Δϵ(θ̄)
f(x, θ̄ + δθ)
! = {G1, …, Gk}maxG∈"
minx∈G
f(x)
![Page 14: Robustness in GANs and in Black-box Optimization · demonstrate much more diversity in generated samples compared to DCGAN. 20 G(z) random “noise” z real data x D(x),D(G(z)) •](https://reader036.vdocument.in/reader036/viewer/2022081607/5ed4605505beeb3a300884e7/html5/thumbnails/14.jpg)
Empirical Results
0 20 40 60 80 100t
0
5
10
15
20
25
‘-re
gret
StableOptGP-UCBMaxiMin-GP-UCBStable-GP-UCBStable-GP-Random
b e t t e r
0 20 40 60 80 100t
≠2
0
2
4
Avg
.M
in.
Obj
.V
al.
GP-UCBMaxiMin-GP-UCBStable-GP-UCBStable-GP-RandomStableOpt
b e t t e r
StableOpt
0 1 2 3x
0
1
2
3
4
y
≠60≠50≠40≠30≠20≠1001020
0 1 2 3x
0
1
2
3
4
y
≠60
≠50
≠40
≠30
≠20
≠10
[Bertsimas et al.’10]
Robot Pushing
Benchmark
![Page 15: Robustness in GANs and in Black-box Optimization · demonstrate much more diversity in generated samples compared to DCGAN. 20 G(z) random “noise” z real data x D(x),D(G(z)) •](https://reader036.vdocument.in/reader036/viewer/2022081607/5ed4605505beeb3a300884e7/html5/thumbnails/15.jpg)
Gaussian Process Regression
-3
-2
-1
0
1
2
3
-2 -1 0 1 2
y(x)
x
Figure: Examples include WiFi localization, C14 callibration curve.
Robustness in ML
Robustness in GANs (Z. Xu, C. Li, S. Jegelka, arXiv)
Representational Power in Deep Learning
Robust Black-Box Optimization (I. Bogunovic, J. Scarlett, S. Jegelka, V.
Cevher NIPS 2018)
One unit is enough!
Robust Optimization, Generalization,
Discrete & Nonconvex Optimization
Generator
Critic
“noise”