no code implementations • 20 Dec 2023 • Sajal Dash, Isaac Lyngaas, Junqi Yin, Xiao Wang, Romain Egele, Guojing Cong, Feiyi Wang, Prasanna Balaprakash
For the training of the 175 Billion parameter model and the 1 Trillion parameter model, we achieved $100\%$ weak scaling efficiency on 1024 and 3072 MI250X GPUs, respectively.
no code implementations • 26 Sep 2023 • Romain Egele, Tyler Chang, Yixuan Sun, Venkatram Vishwanath, Prasanna Balaprakash
Machine learning (ML) methods offer a wide range of configurable hyperparameters that have a significant influence on their performance.
1 code implementation • 28 Jul 2023 • Romain Egele, Isabelle Guyon, Yixuan Sun, Prasanna Balaprakash
Hyperparameter optimization (HPO) is crucial for fine-tuning machine learning models but can be computationally expensive.
no code implementations • 20 Feb 2023 • Romit Maulik, Romain Egele, Krishnan Raghavan, Prasanna Balaprakash
We demonstrate the feasibility of this framework for two tasks - forecasting from historical data and flow reconstruction from sparse sensors for the sea-surface temperature.
no code implementations • 3 Oct 2022 • Matthieu Dorier, Romain Egele, Prasanna Balaprakash, Jaehoon Koo, Sandeep Madireddy, Srinivasan Ramesh, Allen D. Malony, Rob Ross
Distributed data storage services tailored to specific applications have grown popular in the high-performance computing (HPC) community as a way to address I/O and storage challenges.
no code implementations • 1 Jul 2022 • Romain Egele, Isabelle Guyon, Venkatram Vishwanath, Prasanna Balaprakash
Bayesian optimization (BO) is a promising approach for hyperparameter optimization of deep neural networks (DNNs), where each model training can take minutes to hours.
no code implementations • 26 Oct 2021 • Romain Egele, Romit Maulik, Krishnan Raghavan, Bethany Lusch, Isabelle Guyon, Prasanna Balaprakash
However, building ensembles of neural networks is a challenging task because, in addition to choosing the right neural architecture or hyperparameters for each member of the ensemble, there is an added cost of training each model.
no code implementations • 30 Oct 2020 • Romain Egele, Prasanna Balaprakash, Venkatram Vishwanath, Isabelle Guyon, Zhengying Liu
Neural architecture search (NAS) is an AutoML approach that generates and evaluates multiple neural network architectures concurrently and improves the accuracy of the generated models iteratively.
no code implementations • 1 Sep 2019 • Prasanna Balaprakash, Romain Egele, Misha Salim, Stefan Wild, Venkatram Vishwanath, Fangfang Xia, Tom Brettin, Rick Stevens
Cancer is a complex disease, the understanding and treatment of which are being aided through increases in the volume of collected data and in the scale of deployed computing power.