Kernel Semi-Implicit Variational Inference
Semi-implicit variational inference (SIVI) extends traditional variational families with semi-implicit distributions defined in a hierarchical manner. Due to the intractable densities of semi-implicit distributions, classical SIVI often resorts to surrogates of evidence lower bound (ELBO) that would...
Gespeichert in:
Hauptverfasser: | , , , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | Semi-implicit variational inference (SIVI) extends traditional variational
families with semi-implicit distributions defined in a hierarchical manner. Due
to the intractable densities of semi-implicit distributions, classical SIVI
often resorts to surrogates of evidence lower bound (ELBO) that would introduce
biases for training. A recent advancement in SIVI, named SIVI-SM, utilizes an
alternative score matching objective made tractable via a minimax formulation,
albeit requiring an additional lower-level optimization. In this paper, we
propose kernel SIVI (KSIVI), a variant of SIVI-SM that eliminates the need for
lower-level optimization through kernel tricks. Specifically, we show that when
optimizing over a reproducing kernel Hilbert space (RKHS), the lower-level
problem has an explicit solution. This way, the upper-level objective becomes
the kernel Stein discrepancy (KSD), which is readily computable for stochastic
gradient descent due to the hierarchical structure of semi-implicit variational
distributions. An upper bound for the variance of the Monte Carlo gradient
estimators of the KSD objective is derived, which allows us to establish novel
convergence guarantees of KSIVI. We demonstrate the effectiveness and
efficiency of KSIVI on both synthetic distributions and a variety of real data
Bayesian inference tasks. |
---|---|
DOI: | 10.48550/arxiv.2405.18997 |