# Resource frugal optimizer for quantum machine learning

arXiv: https://arxiv.org/abs/2211.04965 · HTML: https://mlsanity.com/paper/2211.04965/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 1 of its 26 references that are in the map.
- First posted on arXiv 9 Nov 2022.

## Builds on (most cited first, 1 of 1)

- [Quark: A Gradient-Free Quantum Learning Framework for Classification Tasks](https://mlsanity.com/paper/2210.01311/) (2022)

## Built on by (most cited first, 3 of 3)

- [Application of quantum-inspired generative models to small molecular datasets](https://mlsanity.com/paper/2304.10867/) (2023)
- [Quantum Machine Learning for Malware Classification](https://mlsanity.com/paper/2305.09674/) (2023)
- [Adaptive directional gradients for parameterised quantum circuits](https://mlsanity.com/paper/2606.09734/) (2026)

## Abstract (arXiv)

Quantum-enhanced data science, also known as quantum machine learning (QML), is of growing interest as an application of near-term quantum computers. Variational QML algorithms have the potential to solve practical problems on real hardware, particularly when involving quantum data. However, training these algorithms can be challenging and calls for tailored optimization procedures. Specifically, QML applications can require a large shot-count overhead due to the large datasets involved. In this work, we advocate for simultaneous random sampling over both the dataset as well as the measurement operators that define the loss function. We consider a highly general loss function that encompasses many QML applications, and we show how to construct an unbiased estimator of its gradient. This allows us to propose a shot-frugal gradient descent optimizer called Refoqus (REsource Frugal Optimizer for QUantum Stochastic gradient descent). Our numerics indicate that Refoqus can save several orders of magnitude in shot cost, even relative to optimizers that sample over measurement operators alone.