# Investigation of D-Wave quantum annealing for training Restricted Boltzmann Machines and mitigating catastrophic forgetting

arXiv: https://arxiv.org/abs/2508.15697 · HTML: https://mlsanity.com/paper/2508.15697/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 47 references that are in the map.
- First posted on arXiv 21 Aug 2025.

## Builds on (most cited first, 19 of 19)

- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Continual Lifelong Learning with Neural Networks: A Review](https://mlsanity.com/paper/1802.07569/) (2018)
- [Continual Learning with Deep Generative Replay](https://mlsanity.com/paper/1705.08690/) (2017)
- [Memory Aware Synapses: Learning what (not) to forget](https://mlsanity.com/paper/1711.09601/) (2017)
- [Learning to Remember: A Synaptic Plasticity Driven Framework for Continual Learning](https://mlsanity.com/paper/1904.03137/) (2019)
- [Generative replay with feedback connections as a general strategy for continual learning](https://mlsanity.com/paper/1809.10635/) (2018)
- [Memory Replay GANs: learning to generate images from new categories without forgetting](https://mlsanity.com/paper/1809.02058/) (2018)
- [Replay in Deep Learning: Current Approaches and Missing Biological Elements](https://mlsanity.com/paper/2104.04132/) (2021)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/2507.10485/) (2025)
- [Application of Quantum Annealing to Training of Deep Neural Networks](https://mlsanity.com/paper/1510.06356/) (2015)
- [Neurogenesis Deep Learning](https://mlsanity.com/paper/1612.03770/) (2016)
- [Training and Classification using a Restricted Boltzmann Machine on the D-Wave 2000Q](https://mlsanity.com/paper/2005.03247/) (2020)
- [S-TRIGGER: Continual State Representation Learning via Self-Triggered Generative Replay](https://mlsanity.com/paper/1902.09434/) (2019)
- [Benchmarking Quantum Hardware for Training of Fully Visible Boltzmann Machines](https://mlsanity.com/paper/1611.04528/) (2016)
- [Comparison of D-Wave Quantum Annealing and Classical Simulated Annealing for Local Minima Determination](https://mlsanity.com/paper/1911.03338/) (2019)
- [Towards Sampling from Nondirected Probabilistic Graphical models using a D-Wave Quantum Annealer](https://mlsanity.com/paper/1905.00159/) (2019)
- [A hybrid quantum-classical approach for inference on restricted Boltzmann machines](https://mlsanity.com/paper/2304.12418/) (2023)
- [Quantum Semantic Learning by Reverse Annealing an Adiabatic Quantum Computer](https://mlsanity.com/paper/2003.11945/) (2020)
- [Comparison of D-Wave Quantum Annealing and Gibbs Monte Carlo for Sampling from a Probability Distribution of a Restricted Boltzmann Machine](https://mlsanity.com/paper/2508.10228/) (2025)

## Abstract (arXiv)

Modest statistical differences between the sampling performances of the D-Wave quantum annealer (QA) and the classical Markov Chain Monte Carlo (MCMC), when applied to Restricted Boltzmann Machines (RBMs), are explored to explain, and possibly address, the absence of significant and consistent improvements in RBM trainability when the D-Wave sampling was used in previous investigations. A novel hybrid sampling approach, combining the classical and the QA contributions, is investigated as a promising way to benefit from the modest differences between the two sampling methods. No improvements in the RBM training are achieved in this work, thereby suggesting that the differences between the QA-based and MCMC sampling, mainly found in the medium-to-low probability regions of the distribution, which are less important for the quality of the sample, are insufficient to benefit the training. Difficulties in achieving sufficiently high quality of embedding RBMs into the lattice of the newer generation of D-Wave hardware could be further complicating the task. On the other hand, the ability to generate samples of sufficient variety from lower-probability parts of the distribution has a potential to benefit other machine learning applications, such as the mitigation of catastrophic forgetting (CF) during incremental learning. The feasibility of using QA-generated patterns of desirable classes for CF mitigation by the generative replay is demonstrated in this work for the first time. While the efficiency of the CF mitigation using the D-Wave QA was comparable to that of the classical mitigation, both the speed of generating a large number of distinct desirable patterns and the potential for further improvement make this approach promising for a variety of challenging machine learning applications.