Application of Langevin Dynamics to Advance the Quantum Natural Gradient Optimization Algorithm (2409.01978v3)
Abstract: A Quantum Natural Gradient (QNG) algorithm for optimization of variational quantum circuits has been proposed recently. In this study, we employ the Langevin equation with a QNG stochastic force to demonstrate that its discrete-time solution gives a generalized form of the above-specified algorithm, which we call Momentum-QNG. Similar to other optimization algorithms with the momentum term, such as the Stochastic Gradient Descent with momentum, RMSProp with momentum and Adam, Momentum-QNG is more effective to escape local minima and plateaus in the variational parameter space and, therefore, achieves a better convergence behavior compared to the basic QNG. In this paper we benchmark Momentum-QNG together with basic QNG, Adam and Momentum optimizers and find the optimal values of its hyperparameters. Our open-source code is available at https://github.com/borbysh/Momentum-QNG
- “A variational eigenvalue solver on a photonic quantum processor.”. Nature Communications 5, 4213 (2014).
- “A quantum approximate optimization algorithm” (2014). arXiv:1411.4028.
- “Classification with quantum neural networks on near term processors” (2018). arXiv:1802.06002.
- “Towards quantum machine learning with tensor networks”. Quantum Science and Technology 4, 024001 (2019).
- “Circuit-centric quantum classifiers”. Physical Review A101 (2020).
- “Evaluating analytic gradients on quantum hardware”. Phys. Rev. A 99, 032331 (2019).
- “Path-sgd: Path-normalized optimization in deep neural networks”. In C. Cortes, N. Lawrence, D. Lee, M. Sugiyama, and R. Garnett, editors, Advances in Neural Information Processing Systems. Volume 28. Curran Associates, Inc. (2015). url: https://proceedings.neurips.cc/paper_files/paper/2015/file/eaa32c96f620053cf442ad32258076b9-Paper.pdf.
- Shun-ichi Amari. “Natural Gradient Works Efficiently in Learning”. Neural Computation 10, 251–276 (1998).
- “Fisher-Rao metric, geometry, and complexity of neural networks”. In Kamalika Chaudhuri and Masashi Sugiyama, editors, Proceedings of the Twenty-Second International Conference on Artificial Intelligence and Statistics. Volume 89 of Proceedings of Machine Learning Research, pages 888–896. PMLR (2019). url: http://proceedings.mlr.press/v89/liang19a/liang19a.pdf.
- “Quantum natural gradient”. Quantum 4, 269 (2020).
- “Adam: A method for stochastic optimization” (2014). arXiv:1412.6980.
- “Learning representations by back-propagating errors.”. Nature 323, 533–536 (1986).
- “Lecture 6e rmsprop: Divide the gradient by a running average of its recent magnitude”. COURSERA: Neural networks for machine learning 4, 26–31 (2012). url: https://www.cs.toronto.edu/~tijmen/csc321/slides/lecture_slides_lec6.pdf.
- O. Borysenko and M. Byshkin. “Coolmomentum: a method for stochastic optimization by Langevin dynamics with simulated annealing.”. Sci Rep 11, 10705 (2021).
- “Langevin dynamics with continuous tempering for training deep neural networks”. In Advances in Neural Information Processing Systems. Pages 618–626. (2017). url: https://proceedings.neurips.cc/paper_files/paper/2017/file/019d385eb67632a7e958e23f24bd07d7-Paper.pdf.
- “Sampling can be faster than optimization”. Proceedings of the National Academy of Sciences 116, 20881–20885 (2019).
- “Quantum Langevin Dynamics for Optimization” (2024). arXiv:2311.15587v2.
- “Accurate sampling using Langevin dynamics”. Physical Review E 75, 056707 (2007).
- “Second-order integrators for Langevin equations with holonomic constraints”. Chemical Physics Letters 429, 310–316 (2006).
- “Algorithms for Brownian dynamics”. Molecular Physics 45, 637–647 (1982).
- Tamar Schlick. “Molecular modeling and simulation: an interdisciplinary guide”. Volume 21 of Interdisciplinary Applied Mathematics. Springer Verlag. (2010). url: https://link.springer.com/book/10.1007/978-1-4419-6351-2.
- “Optimizing Variational Quantum Algorithms with qBang: Efficiently Interweaving Metric and Momentum to Navigate Flat Energy Landscapes”. Quantum 8, 1313 (2024).
- Chi-Chun Chen. https://eric08000800.medium.com/portfolio-optimization-with-variational-quantum-eigensolver-vqe-2-477a0ee4e988 (2023).
- https://github.com/borbysh/Momentum-QNG/blob/main/portfolio_optimization.ipynb (2024).
- “The effect of classical optimizers and ansatz depth on QAOA performance in noisy devices”. Scientific Reports 14, 16011 (2024).
- Jack Ceroni. “Intro to QAOA”. https://pennylane.ai/qml/demos/tutorial_qaoa_intro/ (2024).
- https://github.com/borbysh/Momentum-QNG/blob/main/QAOA_depth4.ipynb (2024).
Sponsor
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.