In this talk we will overview some of our current efforts in using machine learning models and algorithms in order to improve data system performance. In particular, the talk will discuss in length our approach towards improving two key data system functionalities: (i) how to design Learned Approximate Query Processing Engines (based on our Sigmod2019 and CIDR2021 papers) and (ii) how to support random sampling for general n-way join queries (based on our upcoming Sigmod21 paper).

The talk will conclude with an overview of lessons learned and opportunities for future research.

Please email for a Zoom link

Peter Triantafillou is Professor of Data Systems and Head of the Data Sciences Theme at the Department of Computer Science at the University of Warwick, Fellow of the Alan Turing Institute, member of the Advisory Board of the Huawei Ireland Research Centre, member of the Advisory Board of the Urban Big Data Research Centre (a national infrastructure for urban data services and analytics), member of the Advisory Board of PVLDB. Prior to that, Peter held professorial positions at the University of Glasgow, Simon Fraser University in Canada, the Technical University of Crete and University of Patras in Greece and visiting professorships at the Max-Planck Institute for Informatics in Germany. Peter received his PhD in computer science from the University of Waterloo and was the Department of Computer Science and the Faculty of Mathematics nominee for the Gold Medal for outstanding achievements at the Doctoral level. Peter's papers have received numerous awards, including the best paper award at the ACM SIGIR Conference (on Information Retrieval) in 2016, the best paper award at the ACM CIKM Conference (on Information and Knowledge Management) in 2006, the best student paper award at the IEEE Big Data 2018 conference, and the most influential paper award in the ACM DEBS 2019 Conference. Currently, Peter’s group is working on developing and leveraging machine learning models for improving the performance of Data System internals.