MLLGJun 30, 2024

Particle Semi-Implicit Variational Inference

arXiv:2407.00649v311 citations
Originality Highly original
AI Analysis

This addresses a bottleneck in variational inference for machine learning practitioners by enabling more efficient and expressive inference without parametric assumptions.

The paper tackles the intractability of semi-implicit variational inference (SIVI) methods by proposing Particle Variational Inference (PVI), which uses empirical measures to approximate mixing distributions and directly optimizes the evidence lower bound (ELBO), resulting in favorable performance compared to other SIVI methods across various tasks.

Semi-implicit variational inference (SIVI) enriches the expressiveness of variational families by utilizing a kernel and a mixing distribution to hierarchically define the variational distribution. Existing SIVI methods parameterize the mixing distribution using implicit distributions, leading to intractable variational densities. As a result, directly maximizing the evidence lower bound (ELBO) is not possible, so they resort to one of the following: optimizing bounds on the ELBO, employing costly inner-loop Markov chain Monte Carlo runs, or solving minimax objectives. In this paper, we propose a novel method for SIVI called Particle Variational Inference (PVI) which employs empirical measures to approximate the optimal mixing distributions characterized as the minimizer of a free energy functional. PVI arises naturally as a particle approximation of a Euclidean--Wasserstein gradient flow and, unlike prior works, it directly optimizes the ELBO whilst making no parametric assumption about the mixing distribution. Our empirical results demonstrate that PVI performs favourably compared to other SIVI methods across various tasks. Moreover, we provide a theoretical analysis of the behaviour of the gradient flow of a related free energy functional: establishing the existence and uniqueness of solutions as well as propagation of chaos results.

Code Implementations2 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes