Accelerating Convergence in Bayesian Few-Shot Classification
This work addresses a specific bottleneck in few-shot learning for researchers, though it appears incremental as it builds on existing Gaussian process methods.
The paper tackles the challenge of non-conjugate inference in Bayesian few-shot classification by integrating mirror descent-based variational inference with Gaussian processes, resulting in competitive accuracy, improved uncertainty quantification, and faster convergence compared to baselines.
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.