Flow-Transformed Implicit Processes for Function-Space Variational Inference

Excerpt

arXiv:2606.01954v2 Announce Type: replace Abstract: Implicit-process priors define distributions over functions through flexible generative mechanisms, making them attractive for Bayesian function-space modelling. However, performing posterior inference with such priors is challenging because their induced function-space distributions are typically not available in closed form. One practical strategy is to approximate the prior using a finite collection of sampled functions, and then represent p