Скачать с ютуб Implicit generative models: dual and primal approaches в хорошем качестве

Implicit generative models: dual and primal approaches

Iliya Tolstikhin - Postdoc, Max Planck Institute for Intelligent Systems, Tübingen, Germany The fields of unsupervised generative modelling and representation learning are rapidly growing. Empirical success of recently introduced methods, including Variational Auto-Encoders (VAE) and Generative Adversarial Nets (GAN), attracts attention many researchers working in various areas of Machine Learning. Last few years led to unprecedented amount of papers, trying to improve the performance of VAEs/GANs, introducing new versions of these algorithms, and coming up with completely new ideas. In this talk I will try to present a unifying view on many of the existing methods, showing that VAEs/GANs are approaching very similar objectives -- f-divergences, integral probability metrics, optimal transports -- from their primal/dual formulations respectively. I will discuss certain consequences of this duality and mention a recent work on optimal transport, establishing interesting links between VAEs/GANs.