Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new usertexttt{GooStats}: A GPU-based framework for multi-variate analysis in particle physics
80
0
0.0
(
0
)
Authors
Xuefeng Ding
Ask ChatGPT about the research
No Arabic abstract
texttt{GooStats} is a software framework that provides a flexible environment and common tools to implement multi-variate statistical analysis. The framework is built upon the texttt{CERN ROOT}, texttt{MINUIT} and texttt{GooFit} packages. Running a multi-variate analysis in parallel on graphics processing units yields a huge boost in performance and opens new possibilities. The design and benchmark of texttt{GooStats} are presented in this article along with illustration of its application to statistical problems.
rate research
Read More
New heterogeneous computing paradigms on dedicated hardware with increased parallelization, such as Field Programmable Gate Arrays (FPGAs), offer exciting solutions with large potential gains. The growing applications of machine learning algorithms in particle physics for simulation, reconstruction, and analysis are naturally deployed on such platforms. We demonstrate that the acceleration of machine learning inference as a web service represents a heterogeneous computing solution for particle physics experiments that potentially requires minimal modification to the current computing model. As examples, we retrain the ResNet-50 convolutional neural network to demonstrate state-of-the-art performance for top quark jet tagging at the LHC and apply a ResNet-50 model with transfer learning for neutrino event classification. Using Project Brainwave by Microsoft to accelerate the ResNet-50 image classification model, we achieve average inference times of 60 (10) milliseconds with our experimental physics software framework using Brainwave as a cloud (edge or on-premises) service, representing an improvement by a factor of approximately 30 (175) in model inference latency over traditional CPU inference in current experimental hardware. A single FPGA service accessed by many CPUs achieves a throughput of 600--700 inferences per second using an image batch of one, comparable to large batch-size GPU throughput and significantly better than small batch-size GPU throughput. Deployed as an edge or cloud service for the particle physics computing model, coprocessor accelerators can have a higher duty cycle and are potentially much more cost-effective.
The many ways in which machine and deep learning are transforming the analysis and simulation of data in particle physics are reviewed. The main methods based on boosted decision trees and various types of neural networks are introduced, and cutting-edge applications in the experimental and theoretical/phenomenological domains are highlighted. After describing the challenges in the application of these novel analysis techniques, the review concludes by discussing the interactions between physics and machine learning as a two-way street enriching both disciplines and helping to meet the present and future challenges of data-intensive science at the energy and intensity frontiers.
We present an introduction to some concepts of Bayesian data analysis in the context of atomic physics. Starting from basic rules of probability, we present the Bayes theorem and its applications. In particular we discuss about how to calculate simple and joint probability distributions and the Bayesian evidence, a model dependent quantity that allows to assign probabilities to different hypotheses from the analysis of a same data set. To give some practical examples, these methods are applied to two concrete cases. In the first example, the presence or not of a satellite line in an atomic spectrum is investigated. In the second example, we determine the most probable model among a set of possible profiles from the analysis of a statistically poor spectrum. We show also how to calculate the probability distribution of the main spectral component without having to determine uniquely the spectrum modeling. For these two studies, we implement the program Nested fit to calculate the different probability distributions and other related quantities. Nested fit is a Fortran90/Python code developed during the last years for analysis of atomic spectra. As indicated by the name, it is based on the nested algorithm, which is presented in details together with the program itself.
We present a procedure for reconstructing particle cascades from event data measured in a high energy physics experiment. For evaluating the hypothesis of a specific physics process causing the observed data, all possible reconstructi
GELATIO is a new software framework for advanced data analysis and digital signal processing developed for the GERDA neutrinoless double beta decay experiment. The framework is tailored to handle the full analysis flow of signals recorded by high purity Ge detectors and photo-multipliers from the veto counters. It is designed to support a multi-channel modular and flexible analysis, widely customizable by the user either via human-readable initialization files or via a graphical interface. The framework organizes the data into a multi-level structure, from the raw data up to the condensed analysis parameters, and includes tools and utilities to handle the data stream between the different levels. GELATIO is implemented in C++. It relies upon ROOT and its extension TAM, which provides compatibility with PROOF, enabling the software to run in parallel on clusters of computers or many-core machines. It was tested on different platforms and benchmarked in several GERDA-related applications. A stable version is presently available for the GERDA Collaboration and it is used to provide the reference analysis of the experiment data.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
