Samet Oymak


Samet Oymak

Assistant Professor

Electrical and Computer Engineering
Cooperating Faculty with Computer Science

University of California, Riverside

Office: Multidisciplinary Research Building (MRB1) 169 Aberdeen Dr, Riverside, CA 92507

Email: lastname (at) ece (dot) ucr (dot) edu

I am an Assistant Professor of ECE at UC Riverside. I received my PhD degree in Electrical Engineering from Caltech in 2015.

My research lies at the confluence of machine learning, optimization, and statistics. I am broadly interested in finding principled solutions to contemporary
ML problems by using tools from optimization and statistics.

Key question: How to learn with provable guarantees by using minimal compute power, minimal human expertise, & imperfect data?

Current topics: learning with imperfect data, reinforcement learning, autoML & model compression, deep learning theory.

I am looking for enthusiastic PhD and undergraduate students who are interested in ML and data science projects at the intersection of theory and applications.
For PhD: decent grasp of optimization and statistics, For undergrads: basic Python knowledge is necessary. Please reach out with a CV and transcript!


  • 08/2021 Seminar on our NAS work at Stanford Statistics.

  • 08/2021 Our note on super-convergence with large cyclical learning rates is accepted to IEEE Signal Processing Letters!

  • 07/2021 Our MURI proposal on Understanding neuro-glial dynamics for robust non-Markovian learning is funded!

  • 06/2021 Three papers will be presented at RL Theory and Overparameterization Workshops at ICML.

  • 05/2021 I am giving seminars on our recent work at EPFL, Uppsala University, and University of Iowa.

  • 05/2021 New preprint on Certainty Equivalent Quadratic Control for Markov Jump Systems.

  • 04/2021 Our paper on Generalization Guarantees for Neural Architecture Search will appear at ICML 2021.

  • 04/2021 Three papers are presented in TOPML workshop.

  • 04/2021 Our paper on Unsupervised Domain Adaptation is now available (CVPR 2021 oral).

  • 02/2021 New preprint on learning from imbalanced data with Chris’ group.