Provably Robust Training of Quantum Circuit Classifiers Against Parameter Noise

TL;DR

This paper introduces a provably noise-resilient training method for quantum circuit classifiers, enhancing their robustness against parameter noise and enabling more reliable quantum machine learning applications.

Contribution

It develops a provably guaranteed training theory and algorithm for quantum classifiers that is adaptable, noise-resilient, and connects to Evolutionary Strategies.

Findings

Demonstrated robustness in quantum phase classification tasks

Guarantees resilience to parameter noise with minimal algorithm adjustments

Provides a general, function-agnostic training framework for quantum circuits

Abstract

Advancements in quantum computing have spurred significant interest in harnessing its potential for speedups over classical systems. However, noise remains a major obstacle to achieving reliable quantum algorithms. In this work, we present a provably noise-resilient training theory and algorithm to enhance the robustness of parameterized quantum circuit classifiers. Our method, with a natural connection to Evolutionary Strategies, guarantees resilience to parameter noise with minimal adjustments to commonly used optimization algorithms. Our approach is function-agnostic and adaptable to various quantum circuits, successfully demonstrated in quantum phase classification tasks. By developing provably guaranteed optimization theory with quantum circuits, our work opens new avenues for practical, robust applications of near-term quantum computers.