Forward Operator Estimation in Generative Models with Kernel Transfer Operators
This addresses efficiency issues for practitioners using generative models, though it appears incremental as it adapts existing kernel methods.
The paper tackles the computational cost problem in generative models by proposing a cheaper method to estimate the mapping from known to unknown distributions using kernel transfer operators, achieving competitive performance with significant runtime savings.
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).