Accelerating Convergence in Bayesian Few-Shot Classification

TL;DR

This paper introduces a mirror descent-based variational inference method for Gaussian process-based Bayesian few-shot classification, achieving faster convergence, better uncertainty quantification, and competitive accuracy.

Contribution

It integrates mirror descent into Gaussian process models for Bayesian few-shot learning, addressing non-conjugate inference and enhancing convergence speed and invariance properties.

Findings

Faster convergence compared to baseline models

Improved uncertainty quantification

Competitive classification accuracy

Abstract

Bayesian few-shot classification has been a focal point in the field of few-shot learning. This paper seamlessly integrates mirror descent-based variational inference into Gaussian process-based few-shot classification, addressing the challenge of non-conjugate inference. By leveraging non-Euclidean geometry, mirror descent achieves accelerated convergence by providing the steepest descent direction along the corresponding manifold. It also exhibits the parameterization invariance property concerning the variational distribution. Experimental results demonstrate competitive classification accuracy, improved uncertainty quantification, and faster convergence compared to baseline models. Additionally, we investigate the impact of hyperparameters and components. Code is publicly available at https://github.com/keanson/MD-BSFC.