Forward Operator Estimation in Generative Models with Kernel Transfer Operators

Abstract

Generative models which use explicit density modeling (e.g., variational autoencoders, flow-based generative models) involve finding a mapping from a known distribution, e.g. Gaussian, to the unknown input distribution. This often requires searching over a class of non-linear functions (e.g., representable by a deep neural network). While effective in practice, the associated runtime/memory costs can increase rapidly, usually as a function of the performance desired in an application. We propose a much cheaper (and simpler) strategy to estimate this mapping based on adapting known results in kernel transfer operators. We show that our formulation enables highly efficient distribution approximation and sampling, and offers surprisingly good empirical performance that compares favorably with powerful baselines, but with significant runtime savings. We show that the algorithm also performs well in small sample size settings (in brain imaging).

References in corpus (10)

• Auto-Encoding Variational Bayes
• Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Neural Tangent Kernel: Convergence and Generalization in Neural Networks
• VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning
• MMD GAN: Towards Deeper Understanding of Moment Matching Network
• On Exact Computation with an Infinitely Wide Neural Net
• Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Design
• Assessing Generative Models via Precision and Recall
• Eigendecompositions of Transfer Operators in Reproducing Kernel Hilbert Spaces