Hello there, I am Romain Egelé and here is my portfolio!

Follow @Deathn0t

I am a PhD student working on “the Optimization of Learning Workflows at Large Scale on High-Performance Computing Platforms*” under the joint supervision of Prof. Isabelle Guyon and Dr. Prasanna Balaprakash. I have been working on the topic of **Automated Machine Learning since 2018.

Projects

DeepHyper

Open In Colab

Star Fork

Checkout the documentation

Scale Your Search

An Automated Machine Learning tool-box with hyperparameter optimization, neural architecture search, uncertainty quantification, multi-fidelity, warmp starting. Exectuable from a single-laptop to a large scale supercomputer with thousands of parallel workers.


Data-Centric AI

The science of systematically engineering the data of an AI system.

My Contributions

Talks

  • Learning to Discover at Institut Pascal Paris-Saclay (April 2022) [video]

Others Resources

Hubs

  • Data-Centric AI Resource Hub [link]
  • HazyResearch/data-centric-ai [link]

Benchmarks

  • DCAI benchmark [link]

Workshops

  • NeurIPS - DCAI Workshop (December 2021) [link]
  • HAI Stanford University - DCAI Virtual Workshop (November 2021) [link]
  • Snorkel - The future of DCAI (October 2021) [link]
research

2023

  • [preprint] Egele, Romain, Isabelle Guyon, Yixuan Sun, and Prasanna Balaprakash. “Is One Epoch All You Need For Multi-Fidelity Hyperparameter Optimization?.” arXiv preprint arXiv:2307.15422 (2023).
  • [preprint] Maulik, Romit, Romain Egele, Krishnan Raghavan, and Prasanna Balaprakash. “Quantifying uncertainty for deep learning based forecasting and flow-reconstruction using neural architecture search ensembles.” arXiv preprint arXiv:2302.09748 (2023).

2022

  • Dorier, Matthieu, Romain Egele, Prasanna Balaprakash, Jaehoon Koo, Sandeep Madireddy, Srinivasan Ramesh, Allen D. Malony, and Rob Ross. “Hpc storage service autotuning using variational-autoencoder-guided asynchronous bayesian optimization.” In 2022 IEEE International Conference on Cluster Computing (CLUSTER), pp. 381-393. IEEE, 2022.
  • Egele, Romain, Romit Maulik, Krishnan Raghavan, Bethany Lusch, Isabelle Guyon, and Prasanna Balaprakash. “Autodeuq: Automated deep ensemble with uncertainty quantification.” In 2022 26th International Conference on Pattern Recognition (ICPR), pp. 1908-1914. IEEE, 2022.

2021

  • Egele, Romain, Prasanna Balaprakash, Isabelle Guyon, Venkatram Vishwanath, Fangfang Xia, Rick Stevens, and Zhengying Liu. “AgEBO-tabular: joint neural architecture and hyperparameter search with autotuned data-parallel training for tabular data.” In Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1-14. 2021.

2020

  • Maulik, Romit, Romain Egele, Bethany Lusch, and Prasanna Balaprakash. “Recurrent neural network architecture search for geophysical emulation.” In Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1-14. 2020.

2019

  • Balaprakash, Prasanna, Romain Egele, Misha Salim, Stefan Wild, Venkatram Vishwanath, Fangfang Xia, Tom Brettin, and Rick Stevens. “Scalable reinforcement-learning-based neural architecture search for cancer deep learning research.” In Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1-33. 2019.