PeopleofSuperintelligence

Researcher

Andrea Montanari

Andrea Montanari is a Stanford professor whose research focuses on efficient algorithms for noisy data and machine learning. He earned physics degrees at Scuola Normale Superiore in Pisa, worked as a CNRS researcher in Paris, and joined Stanford in 2006. His 2018 paper analyzed training in two-layer neural networks, and a 2024 paper he coauthored on weakly supervised data selection received an ICLR Honorable Mention. He is the John D. and Sigrid Banks Professor in Statistics and Mathematics at Stanford.

Born
1975
Badges
Links
Website

Years link to their sources.

Timeline

  1. 1997–2001

    Physics at Scuola Normale

    He earns a Laurea in physics in 1997 and a PhD in physics in 2001 at Scuola Normale Superiore in Pisa.

  2. 2002–2010

    CNRS research in Paris

    From 2002 to 2010, he works as a Chargé de Recherche with CNRS at Laboratoire de Physique Théorique de l'Ecole Normale Supérieure (LPTENS) in Paris.

  3. 2006–2023

    Stanford faculty roles

    He joins Stanford in 2006 and serves in its Electrical Engineering and Statistics departments through 2023.

  4. 2017–2020

    IEEE and IMS Fellow

    He becomes an IEEE Fellow in 2017 and an IMS Fellow in 2020.

  5. 2018

    Mean-field neural networks

    With Song Mei and Phan-Minh Nguyen, he studies two-layer neural networks trained by stochastic gradient descent. Their 2018 paper shows that a nonlinear partial differential equation captures the training dynamics in a suitable scaling limit.

  6. 2024

    An ICLR honorable mention

    In 2024, he coauthors “Towards a statistical theory of data selection under weak supervision” with Germain Kolossov and Pulkit Tandon. The paper studies data subsets for statistical learning and aims to reduce labeling and computation. ICLR awards it an Honorable Mention, and its results show that some popular selection methods can be substantially suboptimal.

  7. 2025–2026

    Two-layer network dynamics

    In 2025, he and Pierfrancesco Urbani study training dynamics in large two-layer networks and find a separation of time scales. In 2026, he and Zihao Wang derive a threshold for feature learning in two-layer networks. Their paper describes gradient descent as first learning high-gradient directions, then moving into a phase driven by negative Hessian directions.

  8. As of October 2026

    John D. and Sigrid Banks Professor

    As of October 2026, he is the John D. and Sigrid Banks Professor in Statistics and Mathematics at Stanford. His research focuses on efficient algorithms for noisy data across statistics, computer science, information theory, and machine learning.

Career

  1. Since 2006Stanford UniversityJohn D. and Sigrid Banks Professor in Statistics and Mathematics
  2. 2002–2010CNRSChargé de Recherche

Education

  1. 2001Scuola Normale SuperioreLaurea in physics and PhD in physics

From the biography.

  1. 20% of people at companies who shape AI also hold a university role, led by Google and Stanford UniversityIncludes Stanford University. We estimate that 539 of the 6,766 people with a known current organization (8%) hold both a university role and a company role, including 20% of people at companies and 13% of people at universities.
  2. Google had the most people shaping AI every year from 2014 to 2025Includes Stanford University. Our estimates of which organizations employed the most people shaping AI each year from 1955 to 2025, tracing the shift from university labs to companies.
  3. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionIncludes Stanford University. 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.
  4. The company share of AI researchers’ top papers was 31% in 2020–2024 and 8% in 1970–1974Includes Stanford University. 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.

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 Andrea Montanari yet. Send us a free-licensed photo.

  1. Andrea Montanari web.stanford.edu. Checked 20 October 2026.
  2. A Mean Field View of the Landscape of Two-Layers Neural Networks arxiv.org. Checked 20 October 2026.
  3. ICLR 2024 Awards iclr.cc. Checked 20 October 2026.
  4. Towards a statistical theory of data selection under weak supervision proceedings.iclr.cc. Checked 20 October 2026.
  5. Dynamical Decoupling of Generalization and Overfitting in Large Two-Layer Networks arxiv.org. Checked 20 October 2026.
  6. Andrea Montanari's Profile | Stanford Profiles profiles.stanford.edu. Checked 20 October 2026.
  7. Phase Transitions for Feature Learning in Neural Networks arxiv.org. Checked 20 October 2026.