Matteo Riondato

About

Matteo Riondato is an associate professor of computer science at Amherst College, where he leads the Data* Mammoths, a research and learning group composed of undergraduate students. He also serves as the founding director of the Data Science Initiative at Amherst. In addition to his role at Amherst College, he holds an appointment as visiting faculty in Computer Science at Brown University, where he advises PhD students. Prior to his academic positions, he worked as a research scientist in the Labs group at Two Sigma. His research focuses on algorithms for knowledge discovery, data mining, and machine learning. He develops theory and methods aimed at extracting the most information from large datasets as quickly as possible while maintaining statistical soundness. The problems he studies include pattern extraction, graph mining, and time series analysis. His algorithms often incorporate concepts from statistical learning theory and sampling. His research has received support from the National Science Foundation, including an NSF CAREER Award and other NSF awards. Matteo Riondato's academic lineage includes notable mathematicians such as Eli Upfal, Eli Shamir, Jacques Hadamard, Siméon Denis Poisson, and Pierre-Simon Laplace.

Research topics

• Computer science
• Algorithm
• Data mining
• Theoretical computer science
• Mathematics

Selected publications

• DSP: A Statistically-Principled Structural Polarization Measure

  ArXiv.org · 2025-12-03

  preprintOpen access

  Social and information networks may become polarized, leading to echo chambers and political gridlock. Accurately measuring this phenomenon is a critical challenge. Existing measures often conflate genuine structural division with random topological features, yielding misleadingly high polarization scores on random networks, and failing to distinguish real-world networks from randomized null models. We introduce DSP, a Diffusion-based Structural Polarization measure designed from first principle…

  PublisherOA PDFDOI

• Polaris: Sampling from the Multigraph Configuration Model with Prescribed Color Assortativity

  arXiv (Cornell University) · 2024-09-02

  preprintOpen access

  We introduce Polaris, a network null model for colored multi-graphs that preserves the Joint Color Matrix. Polaris is specifically designed for studying network polarization, where vertices belong to a side in a debate or a partisan group, represented by a vertex color, and relations have different strengths, represented by an integer-valued edge multiplicity. The key feature of Polaris is preserving the Joint Color Matrix (JCM) of the multigraph, which specifies the number of edges connecting v…

  PublisherOA PDFDOI

Recent grants

• CAREER: Statistically-Sound Knowledge Discovery from Data

  NSF · $483k · 2023–2028

• III: Small: RUI: Scalable and Iterative Statistical Testing of Multiple Hypotheses on Massive Datasets

  NSF · $373k · 2020–2024

Frequent coauthors

• Eli Upfal

  61 shared

• Mert Akdere

  Brown University

  14 shared

• Fabio Vandin

  University of Padua

  14 shared

• Uğur Çetintemel

  14 shared

• Stanley B. Zdonik

  Brown University

  12 shared

• Cyrus Cousins

  10 shared

• Gianmarco De Francisci Morales

  10 shared

• Giulia Preti

  Centre d'Imagerie BioMedicale

  8 shared

Labs

• Data* MammothsPI

  Research on Algorithms for Knowledge Discovery, Data Mining, and Machine Learning

Education

• Ph.D., Computer Science

  Brown University

  2014

• Sc.M., Computer Science

  Brown University

  2010

• Laurea Specialistica (M.Sc.), Information Engineering

  Università degli Studi di Padova

  2009

• Laurea (B.Sc.), Information Engineering

  Università degli Studi di Padova

  2007

Similar researchers at Brown University

• Michael L. Littmanh-83
• Maurice P Herlihyh-72
• Roberto Tamassiah-69