Quantum Kitchen Sinks: An algorithm for machine learning on near-term quantum computers

TL;DR

This paper introduces quantum kitchen sinks, a hybrid quantum-classical machine learning algorithm that uses quantum circuits to transform data nonlinearly, significantly improving classification accuracy on synthetic and real datasets.

Contribution

It presents a novel hybrid quantum algorithm, quantum kitchen sinks, for machine learning that leverages quantum circuits for nonlinear data transformation, demonstrating substantial performance improvements.

Findings

Quantum circuits improve classification accuracy from 50% to <0.1%.

Small quantum circuits outperform classical linear algorithms.

Full-sized MNIST classification shows modest performance lift.

Abstract

Noisy intermediate-scale quantum computing devices are an exciting platform for the exploration of the power of near-term quantum applications. Performing nontrivial tasks in such devices requires a fundamentally different approach than what would be used on an error-corrected quantum computer. One such approach is to use hybrid algorithms, where problems are reduced to a parameterized quantum circuit that is often optimized in a classical feedback loop. Here we describe one such hybrid algorithm for machine learning tasks by building upon the classical algorithm known as random kitchen sinks. Our technique, called quantum kitchen sinks, uses quantum circuits to nonlinearly transform classical inputs into features that can then be used in a number of machine learning algorithms. We demonstrate the power and flexibility of this proposal by using it to solve binary classification problems for synthetic datasets as well as handwritten digits from the MNIST database. Using the Rigetti quantum virtual machine, we show that small quantum circuits provide significant performance lift over standard linear classical algorithms, reducing classification error rates from 50% to $<0.1\%$, and from $4.1\%$ to $1.4\%$ in these two examples, respectively. Further, we are able to run the MNIST classification problem, using full-sized MNIST images, on a Rigetti quantum processing unit, finding a modest performance lift over the linear baseline.