Simultaneous Perturbation Stochastic Approximation for Few-Shot Learning

TL;DR

This paper introduces a novel SPSA-like approach for few-shot learning that enhances prototypical networks, providing theoretical support and demonstrating superior performance on benchmark datasets.

Contribution

It proposes a new multi-task loss function and an SPSA-inspired method for few-shot learning, improving upon existing prototypical networks.

Findings

Outperforms original prototypical networks on benchmark datasets

Provides theoretical justification for the proposed approach

Shows improved accuracy in few-shot classification tasks

Abstract

Few-shot learning is an important research field of machine learning in which a classifier must be trained in such a way that it can adapt to new classes which are not included in the training set. However, only small amounts of examples of each class are available for training. This is one of the key problems with learning algorithms of this type which leads to the significant uncertainty. We attack this problem via randomized stochastic approximation. In this paper, we suggest to consider the new multi-task loss function and propose the SPSA-like few-shot learning approach based on the prototypical networks method. We provide a theoretical justification and an analysis of experiments for this approach. The results of experiments on the benchmark dataset demonstrate that the proposed method is superior to the original prototypical networks.