Geometrical Insights for Implicit Generative Modeling

نویسندگان

  • Léon Bottou
  • Martín Arjovsky
  • David Lopez-Paz
  • Maxime Oquab
چکیده

Learning algorithms for implicit generative models can optimize a variety of criteria that measure how the data distribution differs from the implicit model distribution, including the Wasserstein distance, the Energy distance, and the Maximum Mean Discrepancy criterion. A careful look at the geometries induced by these distances on the space of probability measures reveals interesting differences. In particular, we can establish surprising approximate global convergence guarantees for the 1-Wasserstein distance, even when the parametric generator has a nonconvex parametrization.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Learning the Base Distribution in Implicit Generative Models

Popular generative model learning methods such as Generative Adversarial Networks (GANs), and Variational Autoencoders (VAE) enforce the latent representation to follow simple distributions such as isotropic Gaussian. In this paper, we argue that learning a complicated distribution over the latent space of an auto-encoder enables more accurate modeling of complicated data distributions. Based o...

متن کامل

An Alternating Direction Implicit Method for Modeling of Fluid Flow

This research includes of the numerical modeling of fluids in two-dimensional cavity. The cavity flow is an important theoretical problem. In this research, modeling was carried out based on an alternating direction implicit via Vorticity-Stream function formulation. It evaluates different Reynolds numbers and grid sizes. Therefore, for the flow field analysis and prove of the ability of the sc...

متن کامل

The Information-Autoencoding Family: A Lagrangian Perspective on Latent Variable Generative Modeling

A variety of learning objectives have been recently proposed for training generative models. We show that many of them, including InfoGAN, ALI/BiGAN, ALICE, CycleGAN, VAE, β-VAE, adversarial autoencoders, AVB, and InfoVAE, are Lagrangian duals of the same primal optimization problem. This generalization reveals the implicit modeling trade-offs between flexibility and computational requirements ...

متن کامل

Learning the Base Distribution in Implicit Generative Models

Popular density estimation methods such as Generative Adversarial Networks (GANs), and Variational Autoencoders (VAE) enforce the latent representation to follow simple distributions such as isotropic Gaussian. In this paper, we claim that learning a complicated distribution over the latent space of an auto-encoder enables accurate modeling over complicated data distributions. We propose a two ...

متن کامل

Geometry Score: A Method For Comparing Generative Adversarial Networks

One of the biggest challenges in the research of generative adversarial networks (GANs) is assessing the quality of generated samples and detecting various levels of mode collapse. In this work, we construct a novel measure of performance of a GAN by comparing geometrical properties of the underlying data manifold and the generated one, which provides both qualitative and quantitative means for...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:
  • CoRR

دوره abs/1712.07822  شماره 

صفحات  -

تاریخ انتشار 2017