Quantum Machine Learning with SQUID

TL;DR

SQUID is an open-source framework integrating quantum and classical methods, enabling efficient training of quantum models for classification tasks like MNIST, with a focus on scalability and gradient-based optimization.

Contribution

The paper introduces SQUID, a standardized, open-source framework combining PyTorch and quantum models for classification, facilitating scalable hybrid quantum-classical algorithms.

Findings

Demonstrated SQUID on MNIST binary classification

Highlighted scalability issues in quantum model output choices

Showcased back-propagation for quantum model training

Abstract

In this work we present the Scaled QUantum IDentifier (SQUID), an open-source framework for exploring hybrid Quantum-Classical algorithms for classification problems. The classical infrastructure is based on PyTorch and we provide a standardized design to implement a variety of quantum models with the capability of back-propagation for efficient training. We present the structure of our framework and provide examples of using SQUID in a standard binary classification problem from the popular MNIST dataset. In particular, we highlight the implications for scalability for gradient-based optimization of quantum models on the choice of output for variational quantum models.