Elad Sarafian

I am an accomplished ML/AI researcher and practitioner with a PhD focused in Reinforcement Learning from Bar-Ilan University. With extensive experience in solving complex problems across diverse fields such as cyber security, audio, and RF, I bring a wealth of expertise to every project. As a seasoned Python programmer, I am passionate about building innovative platforms to empower ML practitioners and streamline their daily tasks.

Selected Publications

Explicit Gradient Learning for Black-Box Optimization

ICML 2020

ICML 2021

ICML 2023

Recomposing the Reinforcement Learning Building Blocks with Hypernetworks
A Coupled Flow Approach to Imitation Learning

Publications

  1. Sarafian, Elad, Mor Sinay, Yoram Louzoun, Noa Agmon, and Sarit Kraus. ”Explicit gradient learning for black-box optimization.” In International Conference on Machine Learning (ICML), pp. 8480-8490. PMLR, 2020. [pdf] [code] [slides]

  2. Sarafian, Elad, Aviv Tamar, and Sarit Kraus. ”Constrained Policy Improvement for Efficient Reinforcement Learning.” IJCAI. 2020. [pdf] [code]

  3. Sarafian, R., Kloog, I., Sarafian, E., Hough, I., & Rosenblatt, J. D. (2020). A Domain Adaptation Approach for Performance Estimation of Spatial Predictions. IEEE Transactions on Geoscience and Remote Sensing. [pdf]

  4. Sarafian, Elad, Shai Keynan, and Sarit Kraus. ”Recomposing the reinforcement learning building blocks with hypernetworks.” International Conference on Machine Learning. PMLR, 2021. [pdf] [code] [slides]

  5. Wexler, Benjamin, Elad Sarafian, and Sarit Kraus. ”Analyzing and Overcoming Degradation in Warm-Start Reinforcement Learning.” 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2022. [pdf] [code]

  6. Freund, Gideon Joseph, Elad Sarafian, and Sarit Kraus. ”A Coupled Flow Approach to Imitation Learning.” International Conference on Machine Learning. PMLR, 2023. [pdf] [code] [slides]

  7. Sarafian, Elad and Tamar, Aviv and Kraus, Sarit, Constrained Policy Improvement for Safe and Efficient Reinforcement Learning, Reinforcement Learning and Decision Making (RLDM), 2019. [pdf]

  8. Sarafian, Elad, and Amir Shlivinski. ”Imaging buried objects in layered media using MUSIC algorithm.” 2010 IEEE 26-th Convention of Electrical and Electronics Engineers in Israel. IEEE, 2010. [pdf]

Résumé

Contact me

Feel free to reach out to us if you have any questions or need assistance with our Python package beam-ds. We are here to help you.

elad.sarafian (at) gmail.com