Related papers: Machine-learning approach for operating electron b…
The hard X-ray instruments at the Linac Coherent Light Source are in the design phase for upgrades that will take full advantage of the high repetition rates that will become available with LCLS-II-HE. The current X-ray Correlation…
Model Agnostic Meta Learning or MAML has become the standard for few-shot learning as a meta-learning problem. MAML is simple and can be applied to any model, as its name suggests. However, it often suffers from instability and…
Machine learning methods usually depend on internal parameters -- so called hyperparameters -- that need to be optimized for best performance. Such optimization poses a burden on machine learning practitioners, requiring expert knowledge,…
The current program at Fermilab involves the construction of a new superconducting linear accelerator (LINAC) to replace the existing warm version. The new LINAC, together with other planned improvements, is in support of proton beam…
This article presents a method that uses turn-by-turn beam position data and k-modulation data to measure the calibration factors of beam position monitors in high energy accelerators. In this method, new algorithms have been developed to…
Existing FEL facilities often suffer from stability issues: so electron orbit, transverse electron optics, electron bunch compression and other parameters have to be readjusted often to account for drifts in performance of various…
Automated tuning of compute kernels is a popular area of research, mainly focused on finding optimal kernel parameters for a problem with fixed input sizes. This approach is good for deploying machine learning models, where the network…
Machine learning algorithms frequently require careful tuning of model hyperparameters, regularization terms, and optimization parameters. Unfortunately, this tuning is often a "black art" that requires expert experience, unwritten rules of…
Parameter-Efficient Fine-Tuning (PEFT) is a popular class of techniques that strive to adapt large models in a scalable and resource-efficient manner. Yet, the mechanisms underlying their training performance and generalization remain…
Particle accelerators are time-varying systems whose components are perturbed by external disturbances. Tuning accelerators can be a time-consuming process involving manual adjustment of multiple components, such as RF cavities, to minimize…
By increasing model parameters but activating them sparsely when performing a task, the use of Mixture-of-Experts (MoE) architecture significantly improves the performance of Large Language Models (LLMs) without increasing the inference…
Beam injections to KEKB and Photon Factory are performed with pulse-to-pulse modulation at 50 Hz. Three very different beams are switched every 20 ms in order to inject those beams into KEKB HER, LER and Photon Factory (PF) simultaneously.…
Online tuning of real-world plants is a complex optimisation problem that continues to require manual intervention by experienced human operators. Autonomous tuning is a rapidly expanding field of research, where learning-based methods,…
Momentum method has been used extensively in optimizers for deep learning. Recent studies show that distributed training through K-step averaging has many nice properties. We propose a momentum method for such model averaging approaches. At…
The massive amount of trainable parameters in the pre-trained language models (PLMs) makes them hard to be deployed to multiple downstream tasks. To address this issue, parameter-efficient transfer learning methods have been proposed to…
KEKB completed all of the technical milestones, and had offered important insights into the flavor structure of elementary particles, especially the CP violation. The accelerator control system at KEKB and injector linac was initiated by a…
Machine learning (ML) has become critical for post-acquisition data analysis in (scanning) transmission electron microscopy, (S)TEM, imaging and spectroscopy. An emerging trend is the transition to real-time analysis and closed-loop…
In order to double the positron injection rate into the KEKB ring, a two-bunch acceleration scheme has been studied at the linac, in which bunches separated by 96 ns are accelerated in 50 Hz. In this scheme the stabilization of energy and…
Extremely Large-scale Array (ELAA) is considered a frontier technology for future communication systems, pivotal in improving wireless systems' rate and spectral efficiency. As ELAA employs a multitude of antennas operating at higher…
Laser wakefield acceleration (LWFA) in a gas cell target separating injection and acceleration section has been investigated to produce high-quality electron beams. A detailed study has been performed on controlling the quality of…