# Training Quantum Boltzmann Machines with Coresets

arXiv: https://arxiv.org/abs/2307.14459 · HTML: https://mlsanity.com/paper/2307.14459/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 47 references that are in the map.
- First posted on arXiv 26 Jul 2023.

## Builds on (most cited first, 12 of 12)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Quantum advantage in learning from experiments](https://mlsanity.com/paper/2112.00778/) (2021)
- [TensorFlow Quantum: A Software Framework for Quantum Machine Learning](https://mlsanity.com/paper/2003.02989/) (2020)
- [Bayesian Coreset Construction via Greedy Iterative Geodesic Ascent](https://mlsanity.com/paper/1802.01737/) (2018)
- [Coresets and Sketches](https://mlsanity.com/paper/1601.00617/) (2016)
- [Small-GAN: Speeding Up GAN Training Using Core-sets](https://mlsanity.com/paper/1910.13540/) (2019)
- [Sparse Variational Inference: Bayesian Coresets from Scratch](https://mlsanity.com/paper/1906.03329/) (2019)
- [SupermarQ: A Scalable Quantum Benchmark Suite](https://mlsanity.com/paper/2202.11045/) (2022)
- [Coreset Clustering on Small Quantum Computers](https://mlsanity.com/paper/2004.14970/) (2020)
- [Resource-Efficient Quantum Computing by Breaking Abstractions](https://mlsanity.com/paper/2011.00028/) (2020)
- [Near-Term Quantum-Classical Associative Adversarial Networks](https://mlsanity.com/paper/1905.13205/) (2019)

## Abstract (arXiv)

Recent work has proposed and explored using coreset techniques for quantum algorithms that operate on classical data sets to accelerate the applicability of these algorithms on near-term quantum devices. We apply these ideas to Quantum Boltzmann Machines (QBM) where gradient-based steps which require Gibbs state sampling are the main computational bottleneck during training. By using a coreset in place of the full data set, we try to minimize the number of steps needed and accelerate the overall training time. In a regime where computational time on quantum computers is a precious resource, we propose this might lead to substantial practical savings. We evaluate this approach on 6x6 binary images from an augmented bars and stripes data set using a QBM with 36 visible units and 8 hidden units. Using an Inception score inspired metric, we compare QBM training times with and without using coresets.