Adaptive autoencoder latent space tuning for more robust machine learning beyond the training set for six-dimensional phase space diagnostics of a time-varying ultrafast electron-diffraction compact accelerator

Scheinker, Alexander; Cropp, Frederick; Filippetto, Daniele

doi:10.1103/PhysRevE.107.045302

Adaptive autoencoder latent space tuning for more robust machine learning beyond the training set for six-dimensional phase space diagnostics of a time-varying ultrafast electron-diffraction compact accelerator

Apr 19, 2023

22 pages

Published in:

Phys.Rev.E 107 (2023) 4, 045302

Published: Apr 19, 2023

DOI:

10.1103/PhysRevE.107.045302 (publication)

reference search17 citations

Citations per year

Abstract: (APS)

We present a general adaptive latent space tuning approach for improving the robustness of machine learning tools with respect to time variation and distribution shift. We demonstrate our approach by developing an encoder-decoder convolutional neural network-based virtual 6D phase space diagnostic of charged particle beams in the HiRES ultrafast electron diffraction (UED) compact particle accelerator with uncertainty quantification. Our method utilizes model-independent adaptive feedback to tune a low-dimensional 2D latent space representation of

\sim 1

million dimensional objects which are the 15 unique 2D projections

(x, y)

,...,

(z, p_{z})

of the 6D phase space

(x, y, z, p_{x}, p_{y}, p_{z})

of the charged particle beams. We demonstrate our method with numerical studies of short electron bunches utilizing experimentally measured UED input beam distributions.

References(62)

Figures(0)

[1]

High-fidelity Prediction of Megapixel Longitudinal Phase-space Images of Electron Beams using Encoder-Decoder Neural Networks

et al.

- Phys.Rev.Applied 16 (2021) 024005
•
e-Print:
- 2101.10437
•
DOI:
- 10.1103/PhysRevApplied.16.024005

[2]

Exact representations of many-body interactions with restricted-Boltzmann-machine neural networks

Ermal Rrapaj
(
- UC, Berkeley and
- Minnesota U.
)
,
Alessandro Roggero
(
- Washington U., Seattle
)

- Phys.Rev.E 103 (2021) 1, 013302
•
e-Print:
- 2005.03568
•
DOI:
- 10.1103/PhysRevE.103.013302

[3]

Accelerating lattice quantum Monte Carlo simulations using artificial neural networks: Application to the Holstein model

S. Li
,
P.M. Dee
,
E. Khatami
,
S. Johnston

- Phys.Rev.B 100 (2019) 020302
•
DOI:
- 10.1103/PhysRevB.100.020302

[4]

Using a Recurrent Neural Network to Reconstruct Quantum Dynamics of a Superconducting Qubit from Physical Observations

E. Flurin
(
- UC, Berkeley and
- BCCP, Berkeley and
- SPEC, Saclay
)
,
L. S. Martin
(
- UC, Berkeley and
- BCCP, Berkeley
)
,
S. Hacohen-Gourgy
(
- UC, Berkeley and
- BCCP, Berkeley and
- Technion
)
,
I. Siddiqi
(
- UC, Berkeley and
- BCCP, Berkeley
)

- Phys.Rev.X 10 (2020) 1, 011006
•
DOI:
- 10.1103/PhysRevX.10.011006

[5]

Adaptive 3D convolutional neural network-based reconstruction method for 3D coherent diffraction imaging

A. Scheinker
,
R. Pokharel

- J.Appl.Phys. 128 (2020) 184901
•
DOI:
- 10.1063/5.0014725

[6]

Reinforcement Learning with Neural Networks for Quantum Feedback

- Phys.Rev.X 8 (2018) 3, 031084
•
DOI:
- 10.1103/PhysRevX.8.031084

[7]

Machine Learning Link Inference of Noisy Delay-Coupled Networks with Optoelectronic Experimental Tests

A. Banerjee
,
J.D. Hart
,
R. Roy
,
E. Ott

- Phys.Rev.X 11 (2021) 031014
•
DOI:
- 10.1103/PhysRevX.11.031014

[8]

Using recurrent neural networks to improve the perception of speech in nonstationary noise by people with cochlear implants

T. Goehring
,
M. Keshavarzi
,
R.P. Carlyon
,
B.C. Moore

- J.Acoust.Soc.Am. 146 (2019) 705
•
DOI:
- 10.1121/1.5119226

[9]

A general-purpose deep learning approach to model time-varying audio effects

M.A.M. Ramírez
,
E. Benetos
,
J.D. Reiss

•
e-Print:
- 1905.06148

[10]

Complex cancer detector: Complex neural networks on non-stationary time series for guiding systematic prostate biopsy, in Medical Image Computing and Computer Assisted Intervention–MICCAI 2020 23rd International Conference, Lima, Peru, Proceedings, Part III 23 (, ), pp

G. Javadi
,
M.N.N. To
,
S. Samadi
,
S. Bayat
,
S. Sojoudi

et al.

[11]

Complex-valued neural networks for machine learning on non-stationary physical data

J.S. Dramsch
,
M. Lüthje
,
A.N. Christensen

- Comput.Geosci. 146 (2021) 104643
•
DOI:
- 10.1016/j.cageo.2020.104643

[12]

Learning deep belief networks from non-stationary streams, in Artificial Neural Networks and Machine Learning–ICANN 2012 22nd International Conference on Artificial Neural Networks, Lausanne, Switzerland, Proceedings, Part II 22 (, Berlin, ), pp

R. Calandra
,
T. Raiko
,
M.P. Deisenroth
,
F.M. Pouzols

[13]

Non-stationary traffic flow prediction using deep learning, in Proceedings of the 2018 IEEE 88th Vehicular Technology Conf. (VTC-Fall) (, Piscataway, NJ, ), pp

A. Koesdwiady
,
S. Bedawi
,
C. Ou
,
F. Karray

[14]

Continual learning with Bayesian neural networks for non-stationary data, in International Conference on Learning Representations (ICLR), Addis Ababa, Ethiopia (OpenReview.net, 2020)

R. Kurle
,
B. Cseke
,
A. Klushyn
,
P. van der Smagt
,
S. Günnemann

[15]

Improving predictive inference under covariate shift by weighting the log-likelihood function

H. Shimodaira

- J.Stat.Plan.Inference 90 (2000) 227
•
DOI:
- 10.1016/S0378-3758(00)00115-4

[16]

in , edited by (, New York, )

G. Peter
,
G. Fishman

[17]

Correcting sample selection Bias by unlabeled data

B. Schölkopf
,
J. Platt
,
T. Hoffman
,
J. Huang
,
A. Gretton

et al.

[18]

Direct importance estimation with model selection and its application to covariate shift adaptation, in (, ), Vol. 7, pp

M. Sugiyama
,
S. Nakajima
,
H. Kashima
,
P. Von Buenau
,
M. Kawanabe

[19]

(, Cambridge, MA, )

M. Sugiyama
,
M. Kawanabe

[20]

Extraction of instantaneous frequencies and amplitudes in nonstationary time-series data

D.E. Shea
,
R. Giridharagopal
,
D.S. Ginger
,
S.L. Brunton
,
J.N. Kutz

- IEEE Access 9 (2021) 83453
•
DOI:
- 10.1109/ACCESS.2021.3087595

[21]

Time-aware Bayesian optimization for adaptive particle accelerator tuning, in Machine Learning and Physical Sciences workshop at the Advances in Neural Information Processing Systems Conference (New Orleans, USA, )

N. Kuklev
,
Y. Sun
,
H. Shang
,
M. Borland
,
G. Fystro

[22]

(, Upper Saddle River, NJ, ), Vol. 3

H.K. Khalil
,
J.W. Grizzle

[23]

Minimum-seeking for CLFs: Universal semiglobally stabilizing feedback under unknown control directions

A. Scheinker
,
M. Krstić

- IEEE Trans. Auto. Control 58 (2012) 1107
•
DOI:
- 10.1109/TAC.2012.2225514

[24]

Simultaneous stabilization and optimization of unknown, time-varying systems, in Proceedings of the 2013 American Control Conference, Washington, DC (, Piscataway, NJ, ), pp

A. Scheinker

[25]

Bounded extremum seeking with discontinuous dithers

A. Scheinker
,
D. Scheinker

- Automatica 69 (2016) 250
•
DOI:
- 10.1016/j.automatica.2016.02.023

1-25 of 62
1
2
3
25 / page