Generative Adversarial Nets ML Reading Group Xiao Lin Jul. 22 2015 Slideshow and powerpoint viewer: • I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville and

Adversarial: a bit of background Visualizing HoG features arXiv 2012 “Why did my detector fail?” ICCV 2013 Visualizing CNNs arXiv 2013 ECCV 2014 CNNs can go wildly wrong arXiv 2013 Generative Adversarial Nets NIPS 2014 Google Deep Dream Facebook Eyescream CVPR 2015 ICLR 2015

A bit of background Visualizing HoG features arXiv 2012 “Why did my detector fail?” ICCV 2013 Visualizing CNNs arXiv 2013 ECCV 2014 CNNs can go wildly wrong arXiv 2013 Generative Adversarial Nets NIPS 2014 Google Deep Dream Facebook Eyescream CVPR 2015 ICLR 2015

A bit of background Visualizing HoG features arXiv 2012 “Why did my detector fail?” ICCV 2013 Visualizing CNNs arXiv 2013 ECCV 2014 CNNs can go wildly wrong arXiv 2013 Generative Adversarial Nets NIPS 2014 Google Deep Dream Facebook Eyescream CVPR 2015 ICLR 2015

A bit of background Visualizing HoG features arXiv 2012 “Why did my detector fail?” ICCV 2013 Visualizing CNNs arXiv 2013 ECCV 2014 CNNs can go wildly wrong arXiv 2013 Generative Adversarial Nets NIPS 2014 Google Deep Dream Facebook Eyescream CVPR 2015 ICLR 2015

A bit of background Visualizing HoG features arXiv 2012 “Why did my detector fail?” ICCV 2013 Visualizing CNNs arXiv 2013 ECCV 2014 CNNs can go wildly wrong arXiv 2013 Generative Adversarial Nets NIPS 2014 Google Deep Dream Facebook Eyescream CVPR 2015 ICLR 2015

A bit of background Visualizing HoG features arXiv 2012 “Why did my detector fail?” ICCV 2013 Visualizing CNNs arXiv 2013 ECCV 2014 CNNs can go wildly wrong arXiv 2013 Generative Adversarial Nets NIPS 2014 Google Deep Dream Facebook Eyescream CVPR 2015 ICLR 2015

A bit of background Visualizing HoG features arXiv 2012 “Why did my detector fail?” ICCV 2013 Visualizing CNNs arXiv 2013 ECCV 2014 CNNs can go wildly wrong arXiv 2013 Generative Adversarial Nets NIPS 2014 Google Deep Dream Facebook Eyescream CVPR 2015 ICLR 2015

Adversarial Framework • Discriminative model • “Police” • Learns to determine whether a sample is from the model distribution of the generative model or the data distribution • Generative model • A team of “counterfeiters” trying to produce fake currency • Try to fool the discriminative model with its model distribution • Until the counterfeits are indistinguishable from the genuine articles • Now the generative model generates a distribution indistinguishable from the data distribution

Related work (Table 2) Given examples. Learn model params Observe part of the example Infer the rest Generate examples according to model distribution Given example. Compute probability Design a model family with parameter θ

Problems • D must be in sync with G • Train G to optimal => all output collapse to 1 point • Tuning parameters • “Enough capacity” • Multi-mode distributions