I am currently a third-year PhD student in the Systems Research Group of the University of Cambridge Computer Laboratory being supervised by Dr Eiko Yoneki. I am also a Doctoral Student at The Alan Turing Institute. My main research interest is the intersection of Machine Learning and Computer systems design. My thesis is on designing computer systems with probabilistic graphical models as building blocks, enabling explainable and robust auto-tuning with Bayesian Optimization and failures recovery using Causal Contextual Bandit.
I obtained a distinction in the MPhil Advanced Computer Science at the University of Cambridge in 2019. I was awarded the Cambridge Trust and the Students of Cambridge awards to fund my MPhil. Before then, I graduated with a first from The University of Manchester in a BSc Computer Science with Industrial Experience. I have received multiple awards in Manchester for improving the students’ life and employability prospects at the department.
Previously I worked at Amazon, Google, and Twitter on large scale distributed systems. I have been to many hackathons where I try quick ideas or implement interesting papers, you can see some of the projects hosted on my GitHub.
- Alabed, Sami, and Eiko Yoneki. “BoGraph: structured bayesian optimization from logs for expensive systems with many parameters.” In Proceedings of the 2nd European Workshop on Machine Learning and Systems, pp. 45-53. 2022. Preprint, Source Code, Slides, Poster, Recording.
- Alabed, Sami, and Eiko Yoneki. “High-Dimensional Bayesian Optimization with Multi-Task Learning for RocksDB.” In Proceedings of the 1st Workshop on Machine Learning and Systems, pp. 111-119. 2021. Proceeding, Slides, Recording.
- Alabed, Sami. “RLCache: Automated Cache Management Using Reinforcement Learning.” arXiv preprint arXiv:1909.13839 (2019). Thesis, Source Code
- Sean Parker, Model-based Reinforcement Learning in Computer Systems.
- Ross Tooley, Auto-tuning Spark with Bayesian Optimization.
Check Dr Eiko’s Yoneki webpage for list of project suggestions I am happy to co-supervise.