On Bayesian Softmax-Gated Mixture-of-Experts Models

TL;DR

This paper provides a comprehensive theoretical analysis of Bayesian mixture-of-experts models with softmax gating, focusing on their asymptotic behavior in density estimation, parameter estimation, and model selection.

Contribution

It establishes posterior contraction rates and convergence guarantees, and proposes strategies for selecting the number of experts, advancing understanding of Bayesian mixture-of-experts models.

Findings

Established posterior contraction rates for density estimation.

Derived convergence guarantees for parameter estimation.

Proposed strategies for selecting the number of experts.

Abstract

Mixture-of-experts models provide a flexible framework for learning complex probabilistic input-output relationships by combining multiple expert models through an input-dependent gating mechanism. These models have become increasingly prominent in modern machine learning, yet their theoretical properties in the Bayesian framework remain largely unexplored. In this paper, we study Bayesian mixture-of-experts models, focusing on the ubiquitous softmax-based gating mechanism. Specifically, we investigate the asymptotic behavior of the posterior distribution for three fundamental statistical tasks: density estimation, parameter estimation, and model selection. First, we establish posterior contraction rates for density estimation, both in the regimes with a fixed, known number of experts and with a random learnable number of experts. We then analyze parameter estimation and derive convergence guarantees based on tailored Voronoi-type losses, which account for the complex identifiability structure of mixture-of-experts models. Finally, we propose and analyze two complementary strategies for selecting the number of experts. Taken together, these results provide one of the first systematic theoretical analyses of Bayesian mixture-of-experts models with softmax gating, and yield several theory-grounded insights for practical model design.