Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

arXiv:2507.11519

Optimizing loading of cold cesium atoms into a hollow-core fiber using machine learning

Anderson, Paul, Sreesh Venuturumilli, Michal Bajcsy

Published Jul 15, 2025• 0 citations
arXivHTMLPDF

Abstract

Experimental multi-parameter optimization can enhance the interfacing of cold atoms with waveguides and cavities. Recent implementations of machine learning (ML) algorithms demonstrate the optimization of complex cold atom ex perimental sequences in a multi-dimensional parameter space. Here, we report on the use of ML to optimize loading of cold atoms into a hollow-core fiber. We use Gaussian process machine learning in M-LOOP, an open-source online machine learning interface, to perform this optimization. This is implemented by iteratively adjusting experimental parameters based on feedback from an atom-counting measurement of optical "bleaching". We test the effectiveness of ML, alongside a manual scan, to converge to optimal loading conditions. We survey multiple ML runs to auto matically access appreciable atom-loading conditions. In conjunction with experimental design choices, ML-assisted optimization holds promise in the implementation and maintenance of complex cold atom experiments.

DOI
10.48550/arxiv.2507.11519

Related papers

Review and experimental benchmarking of machine learning algorithms for efficient optimization of cold atom experiments

Oliver Anton, Victoria Henderson, Elisa Da Ros +4 more

Abstract The generation of cold atom clouds is a complex process which involves the optimization of noisy data in high dimensional parameter spaces. Optimization can be challenging both in and especially outside of the lab due to lack of time, expertise, or access for lengthy manual optimization. In recent years, it was demonstrated that machine learning offers a solution since it can optimize high dimensional problems quickly, without knowledge of the experiment itself. In this paper we present results showing the benchmarking of nine different optimization techniques and implementations, alongside their ability to optimize a rubidium (Rb) cold atom experiment. The investigations are performed on a 3D 87Rb molasses with 10 and 18 adjustable parameters, respectively, where the atom number obtained by absorption imaging was chosen as the test problem. We further compare the best performing optimizers under different effective noise conditions by reducing the signal-to-noise ratio of the images via adapting the atomic vapor pressure in the 2D+ magneto-optical trap and the detection laser frequency stability.

arXiv:2312.13397•Machine Learning Science and Technology•Apr 9, 2024•6 citations

Loading Dynamics of Cold Atoms into a Hollow-Core Photonic Crystal Fiber

Yu Wang, Shijie Chai, Mingjie Xin +3 more

Cold atoms trapped and guided in hollow-core photonic crystal fibers provide a scalable diffraction-free setting for atom–light interactions for quantum technologies. However, due to the mismatch of the depth and spatial extension of the trapping potential from free space to the fiber, the number of cold atoms in the fiber is mainly determined by the loading process from free space to waveguide confinement. Here, we provide a numerical study of the loading dynamics of cold atoms into a hollow-core photonic crystal fiber. We use the Monte Carlo method to simulate the trajectories of an ensemble of cold atoms from free space trapping potential to optical potential inside a hollow-core fiber and calculate the temperature, loading efficiency, and geometry of the ensemble. We also study the noise sources that cause heating and a loss of atoms during the process. Our result could be used to design and optimize the loading process of cold atoms into a hollow-core fiber for cold atom experiments.

Fibers•May 1, 2020•7 citations

Machine-learning-based automated loading of strontium isotopes into magneto-optical trap

Korak Biswas, Kushal Patel, S. Sagar Maurya +2 more

We implemented optimization techniques of machine learning (ML) to obtain the mutually exclusive sets of experimental parameters that maximize the number of strontium atoms of different isotopes (88Sr, 86Sr, and 87Sr) in a magneto-optical trap (MOT). Machine learning optimization techniques are significantly faster than conventional manual optimization. While optimizing the parameters, these algorithms efficiently tackle the problem of being confined in one of the local maxima in the parametric space. Thus, ML can be implemented to automate the loading of different isotopes into MOT to perform multiple experiments in a single setup.

AIP Advances•Jul 1, 2023•2 citations

Fast machine-learning online optimization of ultra-cold-atom experiments

P. B. Wigley, P. J. Everitt, Anton van den Hengel +12 more

We apply an online optimization process based on machine learning to the production of Bose-Einstein condensates (BEC). BEC is typically created with an exponential evaporation ramp that is optimal for ergodic dynamics with two-body s-wave interactions and no other loss rates, but likely sub-optimal for real experiments. Through repeated machine-controlled scientific experimentation and observations our 'learner' discovers an optimal evaporation ramp for BEC production. In contrast to previous work, our learner uses a Gaussian process to develop a statistical model of the relationship between the parameters it controls and the quality of the BEC produced. We demonstrate that the Gaussian process machine learner is able to discover a ramp that produces high quality BECs in 10 times fewer iterations than a previously used online optimization technique. Furthermore, we show the internal model developed can be used to determine which parameters are essential in BEC creation and which are unimportant, providing insight into the optimization process of the system.

arXiv:1507.04964•Scientific Reports•May 16, 2016•226 citations

Machine learning applications in cold atom quantum simulators

Henning Schlömer, Annabelle Bohrdt

As ultracold atom experiments become highly controlled and scalable quantum simulators, they require sophisticated control over high-dimensional parameter spaces and generate increasingly complex measurement data that need to be analyzed and interpreted efficiently. Machine learning (ML) techniques have been established as versatile tools for addressing these challenges, offering strategies for data interpretation, experimental control, and theoretical modeling. In this review, we provide a perspective on how machine learning is being applied across various aspects of quantum simulation, with a focus on cold atomic systems. Emphasis is placed on practical use cases -- from classifying many-body phases to optimizing experimental protocols and representing quantum states -- highlighting the specific contexts in which different ML approaches prove effective. Rather than presenting algorithmic details, we focus on the physical insights enabled by ML and the kinds of problems in quantum simulation where these methods offer tangible benefits.

arXiv:2509.08011•Sep 8, 2025•0 citations

High-efficiency cold-atom transport into a waveguide trap

Ashby Paul Hilton, Christopher Perrella, Fetah Benabid +3 more

Hollow-core optical fibers loaded with cold atoms show great promise as platforms for quantum information processing and highly nonlinear optics, but their limitations have remained poorly understood. Using detailed Monte Carlo simulation, the authors model the loading dynamics and predict the sensitivity of the system to various experimental parameters. Thus guided, they develop an experimental apparatus that can load an order of magnitude more atoms than usual, to yield the extremely high optical depths needed for high-efficiency quantum memories.

arXiv:1802.05396•Physical Review Applied•Oct 12, 2018•23 citations
Experimental multi-parameter optimization can enhance the interfacing of cold atoms with waveguides and cavities. Recent implementations of machine learning (ML) algorithms demonstrate the optimization of complex cold atom ex perimental sequences in a multi-dimensional parameter space. Here, we report on the use of ML to optimize loading of cold atoms into a hollow-core fiber. We use Gaussian process machine learning in M-LOOP, an open-source online machine learning interface, to perform this optimization. This is implemented by iteratively adjusting experimental parameters based on feedback from an atom-counting measurement of optical "bleaching". We test the effectiveness of ML, alongside a manual scan, to converge to optimal loading conditions. We survey multiple ML runs to auto matically access appreciable atom-loading conditions. In conjunction with experimental design choices, ML-assisted optimization holds promise in the implementation and maintenance of complex cold atom experiments.
Abstract The generation of cold atom clouds is a complex process which involves the optimization of noisy data in high dimensional parameter spaces. Optimization can be challenging both in and especially outside of the lab due to lack of time, expertise, or access for lengthy manual optimization. In recent years, it was demonstrated that machine learning offers a solution since it can optimize high dimensional problems quickly, without knowledge of the experiment itself. In this paper we present results showing the benchmarking of nine different optimization techniques and implementations, alongside their ability to optimize a rubidium (Rb) cold atom experiment. The investigations are performed on a 3D 87Rb molasses with 10 and 18 adjustable parameters, respectively, where the atom number obtained by absorption imaging was chosen as the test problem. We further compare the best performing optimizers under different effective noise conditions by reducing the signal-to-noise ratio of the images via adapting the atomic vapor pressure in the 2D+ magneto-optical trap and the detection laser frequency stability.
Cold atoms trapped and guided in hollow-core photonic crystal fibers provide a scalable diffraction-free setting for atom–light interactions for quantum technologies. However, due to the mismatch of the depth and spatial extension of the trapping potential from free space to the fiber, the number of cold atoms in the fiber is mainly determined by the loading process from free space to waveguide confinement. Here, we provide a numerical study of the loading dynamics of cold atoms into a hollow-core photonic crystal fiber. We use the Monte Carlo method to simulate the trajectories of an ensemble of cold atoms from free space trapping potential to optical potential inside a hollow-core fiber and calculate the temperature, loading efficiency, and geometry of the ensemble. We also study the noise sources that cause heating and a loss of atoms during the process. Our result could be used to design and optimize the loading process of cold atoms into a hollow-core fiber for cold atom experiments.
We implemented optimization techniques of machine learning (ML) to obtain the mutually exclusive sets of experimental parameters that maximize the number of strontium atoms of different isotopes (88Sr, 86Sr, and 87Sr) in a magneto-optical trap (MOT). Machine learning optimization techniques are significantly faster than conventional manual optimization. While optimizing the parameters, these algorithms efficiently tackle the problem of being confined in one of the local maxima in the parametric space. Thus, ML can be implemented to automate the loading of different isotopes into MOT to perform multiple experiments in a single setup.
We apply an online optimization process based on machine learning to the production of Bose-Einstein condensates (BEC). BEC is typically created with an exponential evaporation ramp that is optimal for ergodic dynamics with two-body s-wave interactions and no other loss rates, but likely sub-optimal for real experiments. Through repeated machine-controlled scientific experimentation and observations our 'learner' discovers an optimal evaporation ramp for BEC production. In contrast to previous work, our learner uses a Gaussian process to develop a statistical model of the relationship between the parameters it controls and the quality of the BEC produced. We demonstrate that the Gaussian process machine learner is able to discover a ramp that produces high quality BECs in 10 times fewer iterations than a previously used online optimization technique. Furthermore, we show the internal model developed can be used to determine which parameters are essential in BEC creation and which are unimportant, providing insight into the optimization process of the system.
As ultracold atom experiments become highly controlled and scalable quantum simulators, they require sophisticated control over high-dimensional parameter spaces and generate increasingly complex measurement data that need to be analyzed and interpreted efficiently. Machine learning (ML) techniques have been established as versatile tools for addressing these challenges, offering strategies for data interpretation, experimental control, and theoretical modeling. In this review, we provide a perspective on how machine learning is being applied across various aspects of quantum simulation, with a focus on cold atomic systems. Emphasis is placed on practical use cases -- from classifying many-body phases to optimizing experimental protocols and representing quantum states -- highlighting the specific contexts in which different ML approaches prove effective. Rather than presenting algorithmic details, we focus on the physical insights enabled by ML and the kinds of problems in quantum simulation where these methods offer tangible benefits.
Hollow-core optical fibers loaded with cold atoms show great promise as platforms for quantum information processing and highly nonlinear optics, but their limitations have remained poorly understood. Using detailed Monte Carlo simulation, the authors model the loading dynamics and predict the sensitivity of the system to various experimental parameters. Thus guided, they develop an experimental apparatus that can load an order of magnitude more atoms than usual, to yield the extremely high optical depths needed for high-efficiency quantum memories.