PeopleofSuperintelligence

Researcher

Nicolas Vayatis

Nicolas Vayatis is a machine-learning researcher whose work connects statistical learning theory with clinical data. He earned engineering and cognitive-science degrees in 1995, completed a PhD in applied mathematics in 2000, and joined ENS Paris-Saclay in 2007 after academic posts in Barcelona and Paris. With Gilles Blanchard and Gábor Lugosi, he co-authored a 2003 paper on the convergence of regularized boosting classifiers. He co-founded Centre Borelli in 2020, applied machine-learning testing to postural data from Parkinsonian patients in a 2021 study, and was an ELLIS Fellow by 2024. As of October 2026, he is a professor at ENS Paris-Saclay and director of Centre Borelli, and teaches statistical learning in the MVA program.

Born
1971
Works
266
Citations
4,964
h-index
30
Badges

Years link to their sources. Publication numbers from OpenAlex, as of 22 October 2026.

Timeline

  1. 1995–2000

    Engineering and applied mathematics

    He earns an engineering diploma at École Centrale Paris and a DEA in cognitive science at École Polytechnique in 1995, then completes a PhD in applied mathematics at École Polytechnique in 2000.

  2. 2000–2007

    Posts in Spain, Paris and Atlanta

    He takes a Marie Curie postdoctoral position at Universitat Pompeu Fabra in 2000, then becomes a maître de conférences in the LPMA and mathematics department at Université Pierre et Marie Curie in 2002. In 2007, he is a visiting professor at Georgia Tech's School of Mathematics and joins ENS Paris-Saclay as a professor.

  3. 2003

    Regularized boosting classifiers

    With Gilles Blanchard and Gábor Lugosi, he coauthors the 2003 paper “On the Rate of Convergence of Regularized Boosting Classifiers.” The paper introduces penalty-based regularization and derives oracle inequalities showing model adaptivity and rates of classification-error convergence.

  4. 2012–2019

    Directing the CMLA

    From 2012 to 2019, he directs the CMLA (Centre de mathématiques et leurs applications, UMR CNRS 8536). His work on statistical learning includes consistency results for regularized boosting and fast rates under Tsybakov margin conditions.

  5. 2020

    Co-founding Centre Borelli

    From January 2020, he co-founds and directs Centre Borelli, a research unit formed from the CMLA and Cognac G. Its teams bring mathematics, engineering, computing, neurophysiology and clinical research together.

  6. 2021

    Machine learning for fall risk

    With colleagues at Centre Borelli, he coauthors a 2021 PLOS ONE study that uses machine-learning-based multivariate testing on posturographic data from patients with Parkinsonian syndromes. It compares fallers with non-fallers and reports greater front-to-back movements and posturographic area among fallers.

  7. By 2024

    An ELLIS fellowship

    By 2024, he is an ELLIS Fellow, a professor of mathematics at ENS Paris-Saclay and director of Centre Borelli, which he co-founds in 2020.

  8. As of October 2026

    Professor and Centre Borelli director

    As of October 2026, he is a professor at ENS Paris-Saclay and director of Centre Borelli. He teaches the MVA course Introduction to Statistical Learning in the 2026/2027 academic year and leads a September 2026 ENS conference on AI's uses, risks and effects on future science education.

Career

  1. Since 2020Université Paris 8Co-founder, Director
  2. Since 2007École Normale Supérieure Paris-SaclayProfessor
  3. 2021–2026Inserm
  4. 2020–2026Université Paris Cité
  5. 2018–2020Université Paris Sciences et Lettres
  6. 2015–2019Université Paris Descartes
  7. 2015–2020Université Paris-Saclay
  8. 2012–2019CNRSDirector
  9. 2007Georgia Institute of TechnologyVisiting professor
  10. 2002–2007Sorbonne UniversityMaître de conférences
  11. 2000–2002Universitat Pompeu FabraMarie Curie postdoctoral researcher
  12. 1999–2007Institut National des Sciences Mathématiques et de leurs Interactions

Education

  1. 2000École PolytechniquePhD in applied mathematics
  2. 1995École Centrale ParisEngineering diploma
  3. 1995École PolytechniqueDEA in cognitive science

From the biography and OpenAlex affiliations (the years of papers that list the organization), so some years are approximate.

Most-cited works

  1. Selective review of offline change point detection methods2019 · Signal Processing · 1,350 citations
  2. A review of center of pressure (COP) variables to quantify standing balance in elderly people: Algorithms and open‐access code2021 · Physiological Reports · 351 citations
  3. Ranking and Empirical Minimization of U-statistics2008 · The Annals of Statistics · 275 citationsWith Gábor Lugosi
  4. On the Bayes-risk consistency of regularized boosting methods2004 · The Annals of Statistics · 185 citationsWith Gábor Lugosi
  5. Parallel Gaussian process optimization with upper confidence bound and pure exploration2013 · 144 citations

From OpenAlex, as of 21 October 2026.

  1. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other universityIncludes Université Paris-Saclay. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other university. We compare doctorate and 5+ year employment links, career timing and current workplaces for 187 major-prize and 1,111 best-paper winners.
  2. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionIncludes Université Paris-Saclay. We estimate where the people shaping AI studied and where their careers led. Massachusetts Institute of Technology leads with 467 former students, including 291 recorded doctorates.
  3. The company share of AI researchers’ top papers was 31% in 2020–2024 and 8% in 1970–1974Includes Université Paris-Saclay. We estimate where the people shaping AI worked when their most-cited papers appeared: the company share was 31% in 2020–2024 and 8% in 1970–1974, and Google led all organizations in 2020–2024.
  4. Google has the highest combined h-index among AI organizationsIncludes Université Paris-Saclay. We estimate that Google holds the highest combined h-index at 8,016, while universities account for 73% of the deduplicated total across AI organizations.

Colleagues

People named in this biography, and people with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of Nicolas Vayatis yet. Send us a free-licensed photo.

  1. Nicolas VAYATIS | Centre Borelli centreborelli.ens-paris-saclay.fr. Checked 20 October 2026.
  2. On the Rate of Convergence of Regularized Boosting Classifiers jmlr.org. Checked 20 October 2026.
  3. Des algorithmes, des cerveaux et des hommes (L'Edition #12) | Université Paris-Saclay universite-paris-saclay.fr. Checked 20 October 2026.
  4. Revealing posturographic profile of patients with Parkinsonian syndromes through a novel hypothesis testing framework based on machine learning | PLOS ONE journals.plos.org. Checked 20 October 2026.
  5. Séminaire : IA HYBRIDE - Aristote association-aristote.fr. Checked 20 October 2026.
  6. Nicolas VAYATIS - MVA/IAS nvayatis.perso.math.cnrs.fr. Checked 20 October 2026.
  7. Actions de formation autour de l’intelligence artificielle | ENS-PARIS-SACLAY ens-paris-saclay.fr. Checked 20 October 2026.