2.7k citations · 8.5k across the 41 of their papers we have counts for
Showing 2017Show all
2 papers · 1 filter
stat.ML2017★ 102 cited
Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Step
William Fedus, Mihaela Rosca, Balaji Lakshminarayanan +3
Generative adversarial networks (GANs) are a family of generative models that do not minimize a single training criterion. Unlike other generative models, the data distribution is…
cs.LG2017
Who Said What: Modeling Individual Labelers Improves Classification
Melody Y. Guan, Varun Gulshan, Andrew M. Dai +1
Data are often labeled by many different experts with each expert only labeling a small fraction of the data and each data point being labeled by several experts. This reduces the…