Applications of Deep Learning to physics workflows
Abstract
Modern large-scale physics experiments create datasets with sizes and streaming rates that can exceed those from industry leaders such as Google Cloud and Netflix. Fully processing these datasets requires both sufficient compute power and efficient workflows. Recent advances in Machine Learning (ML) and Artificial Intelligence (AI) can either improve or replace existing domain-specific algorithms to increase workflow efficiency. Not only can these algorithms improve the physics performance of current algorithms, but they can often be executed more quickly, especially when run on coprocessors such as GPUs or FPGAs. In the winter of 2023, MIT hosted the Accelerating Physics with ML at MIT workshop, which brought together researchers from gravitational-wave physics, multi-messenger astrophysics, and particle physics to discuss and share current efforts to integrate ML tools into their workflows. The following white paper highlights examples of algorithms and computing frameworks discussed during this workshop and summarizes the expected computing needs for the immediate future of the involved fields.
Keywords
Cite
@article{arxiv.2306.08106,
title = {Applications of Deep Learning to physics workflows},
author = {Manan Agarwal and Jay Alameda and Jeroen Audenaert and Will Benoit and Damon Beveridge and Meghna Bhattacharya and Chayan Chatterjee and Deep Chatterjee and Andy Chen and Muhammed Saleem Cholayil and Chia-Jui Chou and Sunil Choudhary and Michael Coughlin and Maximilian Dax and Aman Desai and Andrea Di Luca and Javier Mauricio Duarte and Steven Farrell and Yongbin Feng and Pooyan Goodarzi and Ekaterina Govorkova and Matthew Graham and Jonathan Guiang and Alec Gunny and Weichangfeng Guo and Janina Hakenmueller and Ben Hawks and Shih-Chieh Hsu and Pratik Jawahar and Xiangyang Ju and Erik Katsavounidis and Manolis Kellis and Elham E Khoda and Fatima Zahra Lahbabi and Van Tha Bik Lian and Mia Liu and Konstantin Malanchev and Ethan Marx and William Patrick McCormack and Alistair McLeod and Geoffrey Mo and Eric Anton Moreno and Daniel Muthukrishna and Gautham Narayan and Andrew Naylor and Mark Neubauer and Michael Norman and Rafia Omer and Kevin Pedro and Joshua Peterson and Michael Pürrer and Ryan Raikman and Shivam Raj and George Ricker and Jared Robbins and Batool Safarzadeh Samani and Kate Scholberg and Alex Schuy and Vasileios Skliris and Siddharth Soni and Niharika Sravan and Patrick Sutton and Victoria Ashley Villar and Xiwei Wang and Linqing Wen and Frank Wuerthwein and Tingjun Yang and Shu-Wei Yeh},
journal= {arXiv preprint arXiv:2306.08106},
year = {2023}
}
Comments
Whitepaper resulting from Accelerating Physics with ML@MIT workshop in Jan/Feb 2023