Matteo Riondato

Head shot of Matteo Riondato
				by Andrea Podestà

Contact info

I am a researcher in computer science, currently with the Labs group at Two Sigma, a highly innovative investment firm in New York City. I also have an appointment as Adjunct Assistant Professor of Computer Science at Brown University.

My research interest is in algorithmic data science. I develop theory and methods to extract the most information from large datasets, as fast as possible and in a statistically sound way. The problems I study include pattern extraction, graph mining, and time series analysis. My algorithms often use concepts from statistical learning theory and sampling.

My Erdős number is 3 (ErdősSuenUpfal → Matteo), and I am a mathematical descendant of Eli Upfal, Eli Shamir (2nd generation), Jacques Hadamard (5th), Siméon Denis Poisson (9th), and Pierre-Simon Laplace (10th).


  • KDD'18: MiSoSouP, our algorithm for subgroup discovery using random sampling and pseudodimension has been accepted for long presentation at KDD'18. Joint work with superstar co-author Fabio Vandin. Very happy that all the work we put in this paper paid off.
  • SDM'19: I'll be serving as co-chair of the Doctoral Forum for SIAM SDM'19. Very excited to help with the organization, as I won the best student poster award at this event in 2014.
  • HLF'18: I have been selected as a Young Researcher for the Heidelberg Laureate Forum! Really excited to go meet brilliant minds of all ages in September.
  • ACM TKDD: ABRA, our work (with Eli) on approximating betweenness centrality with Rademacher averages was accepted for publication in ACM TKDD.
  • FouLarD'18: I'm co-organizing FouLarD'18, a workshop on the foundations of learning from data, together with Mehryar Mohri, Alessandro Panconesi, and Eli Upfal. It will take place in Bertinoro, Italy, in September 2018.
  • IEEE ICDM'18: I'm serving on the PC of IEEE ICDM'18, which will be in Singapore in November.
  • ECML PKDD'18: Happy to serve on the PC of ECML PKDD'18, my "home" conference in many ways, and a great venue for algorithmic data science.
  • News archive