Quantum-Aided Meta-Learning for Bayesian Binary Neural Networks via Born Machines

TL;DR

This paper introduces a quantum-assisted meta-learning approach that uses Born machines to model variational distributions in Bayesian binary neural networks, improving training efficiency across multiple tasks.

Contribution

It combines quantum probabilistic models with meta-learning for Bayesian neural networks, a novel integration enhancing data efficiency and performance.

Findings

Outperforms conventional joint learning strategies in regression tasks

Uses quantum Born machines to model binary neural network weights

Reduces training data requirements for new tasks

Abstract

Near-term noisy intermediate-scale quantum circuits can efficiently implement implicit probabilistic models in discrete spaces, supporting distributions that are practically infeasible to sample from using classical means. One of the possible applications of such models, also known as Born machines, is probabilistic inference, which is at the core of Bayesian methods. This paper studies the use of Born machines for the problem of training binary Bayesian neural networks. In the proposed approach, a Born machine is used to model the variational distribution of the binary weights of the neural network, and data from multiple tasks is used to reduce training data requirements on new tasks. The method combines gradient-based meta-learning and variational inference via Born machines, and is shown in a prototypical regression problem to outperform conventional joint learning strategies.