Abstract
While the interaction of ultra-intense ultra-short laser pulses with near- and overcritical plasmas cannot be directly observed, experimentally accessible quantities (observables) often only indirectly give information about the underlying plasma dynamics. Furthermore, the information provided by observables is incomplete, making the inverse problem highly ambiguous. Therefore, in order to infer plasma dynamics as well as experimental parameter, the full distribution over parameters given an observation needs to considered, requiring that models are flexible and account for the information lost in the forward process. Invertible Neural Networks (INNs) have been designed to efficiently model both the forward and inverse process, providing the full conditional posterior given a specific measurement. In this work, we benchmark INNs and standard statistical methods on synthetic electron spectra. First, we provide experimental results with respect to the acceptance rate, where our results show increases in acceptance rates up to a factor of 10. Additionally, we show that this increased acceptance rate also results in an increased speed-up for INNs to the same extent. Lastly, we propose a composite algorithm that utilizes INNs and promises low runtimes while preserving high accuracy.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
Sometimes (unfortunately) also called electron temperature.
- 2.
Or, equivalently, the maximum ion energy in a laser-driven ion spectrum.
- 3.
Note that we use, for the sake of better of readability, henceforth the symbol \(\textbf{x}\) both for our simulation parameter \(\textbf{x}\) as well as normalized ML parameter \(\hat{\textbf{x}}\).
- 4.
Not including ActNorm, invertible 1\(\,\times \,\)1 convolutions, etc. relevant for their specific application, but only the coupling part itself.
- 5.
I.e. 4000 and 1000 data points for the train and test set, respectively.
References
Ardizzone, L., Kruse, J., Rother, C., Köthe, U.: Analyzing inverse problems with invertible neural networks (2018). http://arxiv.org/abs/10.48550/ARXIV.1808.04730
Beaumont, M.A.: Approximate bayesian computation. Ann. Rev. Stat. Appl. 6, 379–403 (2019). https://doi.org/10.1146/annurev-statistics-030718-105212
Birdsall, C.K., Langdon, A.B.: Plasma Physics via Computer Simulation. CRC Press, Boca Raton (2018)
Burau, H., et al.: Picongpu: a fully relativistic particle-in-cell code for a GPU cluster. IEEE Trans. Plasma Sci. 38(10), 2831–2839 (2010). https://doi.org/10.1109/tps.2010.2064310
Derouillat, J., et al.: Smilei: a collaborative, open-source, multi-purpose particle-in-cell code for plasma simulation. Comput. Phys. Commun. 222, 351–373 (2018). https://doi.org/10.1016/j.cpc.2017.09.024
Dinh, L., Krueger, D., Bengio, Y.: Nice: Non-linear independent components estimation. arXiv preprint arXiv:1410.8516 (2014). https://doi.org/10.48550/ARXIV.1410.8516
Dinh, L., Sohl-Dickstein, J., Bengio, S.: Density estimation using real NVP (2016). https://doi.org/10.48550/ARXIV.1605.08803
Djordjević, B.Z., et al.: Modeling laser-driven ion acceleration with deep learning. Phys. Plasmas 28(4), 043105 (2021). https://doi.org/10.1063/5.0045449
Gibbon, P.: Short-Pulse Laser Interactions with Matter: an Introduction. World Scientific, Singapore (2005)
Gretton, A., Borgwardt, K.M., Rasch, M.J., Schölkopf, B., Smola, A.: A kernel two-sample test. J. Mach. Learn. Res. 13(1), 723–773 (2012)
Hockney, R.W., Eastwood, J.W.: Computer Simulation using Particles. CRC Press, Boca Raton (2021)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization (2014). https://doi.org/10.48550/ARXIV.1412.6980
Kingma, D.P., Dhariwal, P.: Glow: Generative flow with invertible 1x1 convolutions. In: Advances in Neural Information Processing Systems, vol. 31 (2018)
Kluge, T., Cowan, T., Debus, A., Schramm, U., Zeil, K., Bussmann, M.: Electron temperature scaling in laser interaction with solids. Phys. Rev. Lett. 107(20), 205003 (2011). https://doi.org/10.1103/PhysRevLett.107.205003
Macchi, A.: A review of laser-plasma ion acceleration (2017). https://doi.org/10.48550/ARXIV.1712.06443
Mora, P.: Plasma expansion into a vacuum. Phys. Rev. Lett. 90(18), 185002 (2003). https://doi.org/10.1103/PhysRevLett.90.185002
Niederreiter, H.: Random number generation and quasi-monte Carlo methods. SIAM (1992). https://doi.org/10.1137/1.9781611970081
Russel, S., Norvig, P., et al.: Artificial Intelligence: A Modern Approach. Pearson Education Limited, London (2013)
Wilks, S.C., et al.: Energetic proton generation in ultra-intense laser-solid interactions. Phys. Plasmas 8(2), 542–549 (2001). https://doi.org/10.1063/1.1333697
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Miethlinger, T., Hoffmann, N., Kluge, T. (2023). Acceptance Rates of Invertible Neural Networks on Electron Spectra from Near-Critical Laser-Plasmas: A Comparison. In: Wyrzykowski, R., Dongarra, J., Deelman, E., Karczewski, K. (eds) Parallel Processing and Applied Mathematics. PPAM 2022. Lecture Notes in Computer Science, vol 13827. Springer, Cham. https://doi.org/10.1007/978-3-031-30445-3_23
Download citation
DOI: https://doi.org/10.1007/978-3-031-30445-3_23
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-30444-6
Online ISBN: 978-3-031-30445-3
eBook Packages: Computer ScienceComputer Science (R0)