Semi-Implicit Variational Inference via Kernelized Path Gradient Descent

MCML Authors

Tobias Pielok

* Former Member

→ Group Bernd Bischl
 Statistical Learning and Data Science

Bernd Bischl

Prof. Dr.

Director

Statistical Learning and Data Science

David Rügamer

Prof. Dr.

Core PI

Statistics, Data Science and Machine Learning

Abstract

Semi-implicit variational inference (SIVI) is a powerful framework for approximating complex posterior distributions, but training with the Kullback-Leibler (KL) divergence can be challenging due to high variance and bias in high-dimensional settings. While current state-of-the-art semi-implicit variational inference methods, particularly Kernel Semi-Implicit Variational Inference (KSIVI), have been shown to work in high dimensions, training remains moderately expensive. In this work, we propose a kernelized KL divergence estimator that stabilizes training through nonparametric smoothing. To further reduce the bias, we introduce an importance sampling correction. We provide a theoretical connection to the amortized version of the Stein variational gradient descent, which estimates the score gradient via Stein's identity, showing that both methods minimize the same objective, but our semi-implicit approach achieves lower gradient variance. In addition, our method's bias in function space is benign, leading to more stable and efficient optimization. Empirical results demonstrate that our method outperforms or matches state-of-the-art SIVI methods in both performance and training efficiency.

inproceedings PBR26

---

AISTATS 2026

29th International Conference on Artificial Intelligence and Statistics. Tangier, Morocco, May 02-05, 2026. To be published. Preprint available.

---

Authors

T. Pielok • B. Bischl • D. Rügamer

---

Links

arXiv

---

Research Area

 A1 | Statistical Foundations & Explainability