1.
|
|
2.
|
|
Accelerating hyperparameter optimization using performance prediction on a heterogeneous HPC system
/ Garcia Amboage, Juan Pablo (speaker) (Universidade de Santiago de Compostela (ES))
Training and hyperparameter optimization (HPO) of deep learning-based (DL) AI models is often compute resource intensive and calls for the use of large-scale distributed resources as well as scalable and resource efficient hyperparameter search and evaluation algorithms. In this context, performance prediction emerges as a potential approach to accelerate the HPO process.Using meta-models, referred to as performance predictors, it is possible to estimate the performance of a given configuration at a particular epoch by leveraging information from its partial learning curve. [...]
2023 - 2879.
CERN Computing Seminar | openlab series
External link: Event details
In : Accelerating hyperparameter optimization using performance prediction on a heterogeneous HPC system
|
|
3.
|
|
4.
|
Distributed hybrid quantum-classical performance prediction for hyperparameter optimization
/ Wulff, Eric (CERN) ; Garcia Amboage, Juan Pablo (CERN) ; Aach, Marcel (Julich, Forschungszentrum ; Iceland U.) ; Gislason, Thorsteinn Eli (Iceland U.) ; Ingolfsson, Thorsteinn Kristinn (Iceland U.) ; Ingolfsson, Tomas Kristinn (Iceland U.) ; Pasetto, Edoardo (Julich, Forschungszentrum ; RWTH Aachen U.) ; Delilbasic, Amer (Julich, Forschungszentrum ; Iceland U.) ; Riedel, Morris (Julich, Forschungszentrum ; Iceland U.) ; Sarma, Rakesh (Julich, Forschungszentrum) et al.
Hyperparameter optimization (HPO) of neural networks is a computationally expensive procedure, which requires a large number of different model configurations to be trained. To reduce such costs, this work presents a distributed, hybrid workflow, that runs the training of the neural networks on multiple graphics processing units (GPUs) on a classical supercomputer, while predicting the configurations’ performance with quantum-trained support vector regression (QT-SVR) on a quantum annealer (QA). [...]
2024 - 14 p.
- Published in : Quantum Machine Intelligence 6 (2024) 59
Fulltext: PDF;
|
|
5.
|
|
Hyperparameter Optimization for Deep Learning Models Using High Performance Computing
/ Wulff, Eric (speaker) (CERN)
Abstract
In the past decade, Machine Learning (ML), and in particular Deep Learning (DL), has outperformed traditional rule-based algorithms on a wide variety of tasks, such as for instance image recognition, object detection and natural language processing. In CoE RAISE, we have additionally seen that ML can unlock new potential in fields such as high energy physics (HEP), remote sensing, seismic imaging, additive manufacturing, and acoustics. [...]
2024 - 4364.
CERN openlab summer student lecture programme
External link: Event details
In : Hyperparameter Optimization for Deep Learning Models Using High Performance Computing
|
|
6.
|
|
Hyperparameter Optimization for Deep Learning Models Using High Performance Computing
/ Wulff, Eric (speaker) (CERN)
AbstractIn the past decade, Machine Learning (ML), and especially Deep Learning (DL), has outperformed traditional rule-based algorithms on a wide variety of tasks, such as for instance image recognition, object detection and natural language processing. In CoE RAISE, we have additionally seen that ML can unlock new potential in fields such as high energy physics (HEP), remote sensing, seismic imaging, additive manufacturing, and acoustics. [...]
2023 - 4408.
CERN openlab summer student lecture programme
External link: Event details
In : Hyperparameter Optimization for Deep Learning Models Using High Performance Computing
|
|
7.
|
Hyperparameter optimization of data-driven AI models on HPC systems
/ Wulff, Eric (CERN) ; Girone, Maria (CERN) ; Pata, Joosep (NICPB, Tallinn)
In the European Center of Excellence in Exascale computing "Research on AI- and Simulation-Based Engineering at Exascale" (CoE RAISE), researchers develop novel, scalable AI technologies towards Exascale. This work exercises High Performance Computing resources to perform large-scale hyperparameter optimization using distributed training on multiple compute nodes. [...]
arXiv:2203.01112.-
2023 - 6 p.
- Published in : J. Phys. : Conf. Ser.: 2438 (2023) , no. 1, pp. 012092
Fulltext: document - PDF; 2203.01112 - PDF;
In : 20th International Workshop on Advanced Computing and Analysis Techniques in Physics Research (ACAT 2021), Daejeon, Korea, 29 Nov - 3 Dec 2021, pp.012092
|
|
8.
|
|
Hyperparameter Optimization for Deep Learning Models Using High Performance Computing
/ Wulff, Eric (speaker) (CERN)
In the past decade, Machine Learning (ML), and in particular Deep Learning (DL), has outperformed traditional rule-based algorithms on a wide variety of tasks, such as for instance image recognition, object detection and natural language processing. In CoE RAISE, we have additionally seen that ML can unlock new potential in fields such as high energy physics (HEP), remote sensing, seismic imaging, additive manufacturing, and acoustics. [...]
2023 - 3434.
EP-IT Data Science Seminars
External link: Event details
In : Hyperparameter Optimization for Deep Learning Models Using High Performance Computing
|
|
9.
|
|
|
High-energy Fission around Z=82,78 Measured with an Optical Chamber
/ Caamano, Manuel (University of Santiago de Compostela, 15782 Santiago de Compostela, Spain) ; Fernandez-Dominguez, Beatriz (University of Santiago de Compostela, 15782 Santiago de Compostela, Spain) ; Alvarez-Pol, Hector (University of Santiago de Compostela, 15782 Santiago de Compostela, Spain) ; Cabanelas, Pablo (University of Santiago de Compostela, 15782 Santiago de Compostela, Spain) ; Gonzalez-Diaz, Diego (University of Santiago de Compostela, 15782 Santiago de Compostela, Spain)
CERN-INTC-2017-065 ; INTC-I-193.
-
2017.
Fulltext
|
|
10.
|
|