AI People Wiki
Portrait of Trevor Hastie
Photo: Trevor Hastie (made using a tripod and…, CC BY-SA 3.0. Credit

Builders & open source

Trevor Hastie

The John A. Overdeck Professor, Professor of Statistics, Professor of Biomedical Data Science, Emeritus, Stanford University

  • The John A. Overdeck Professor, Professor of Statistics, Professor of Biomedical Data Science, Emeritus, Stanford University15

Trevor Hastie is the John A. Overdeck Professor and Professor of Statistics and of Biomedical Data Science, Emeritus, at Stanford University, where Hastie held a joint appointment from 1994 to 2025 after nine years at AT&T Bell Laboratories. Hastie is an author and the maintainer of glmnet, the R package for lasso and elastic-net regularized generalized linear models, whose version 5.0 replaced its Fortran code with C++. With Robert Tibshirani and Jerome Friedman, Hastie wrote The Elements of Statistical Learning, and the authors offer the book as a PDF download; Hastie also co-wrote An Introduction to Statistical Learning, in R and Python editions.1234

At a glance

Current role
The John A. Overdeck Professor, Professor of Statistics, Professor of Biomedical Data Science, Emeritus
Sector
University
Education
Stanford
Work listed
3
Sources cited
8
Profile reviewed

Research

Hastie completed a PhD at Stanford in 1985 with a dissertation on principal curves and surfaces, with Stuetzle listed as advisor. Stanford's Department of Statistics describes Hastie's main research contributions as applied nonparametric regression and classification, along with statistical computing, and notes later work on applied problems in biology, genomics, medicine and industry.5

Hastie's more recent papers include a 2017 extended comparison, with Robert and Ryan Tibshirani, of best subset selection, forward stepwise selection and the lasso, and a 2019 study with Andrea Montanari, Saharon Rosset and Ryan Tibshirani on the behavior of ridgeless least squares interpolation in high dimensions.67

Books and software

With Robert Tibshirani, Hastie wrote "Generalized Additive Models" (1991), and with John Chambers co-edited "Statistical Models in S" (1992), a library of modeling tools for the S-PLUS language. Hastie, Tibshirani and Jerome Friedman then wrote "The Elements of Statistical Learning", first published by Springer in 2001.5

Hastie is a co-author, with Gareth James, Daniela Witten and Robert Tibshirani, of "An Introduction to Statistical Learning", a less technical treatment of the field with a lab in each chapter. Its first R edition was released in 2013, a second edition followed in 2021 and a Python edition in 2023. Hastie is also an author and the maintainer of glmnet, an R package for fitting lasso and elastic-net regularization paths for generalized linear models.42

Work and contributions

  • glmnet Open-source code

    Listed on CRAN as an author and the maintainer of glmnet, which fits lasso and elastic-net regularized generalized linear models and is published under GPL-2. Hastie's homepage notes that glmnet 5.0 (May 2026) replaced all Fortran code with C++.281

  • The Elements of Statistical Learning Published research

    Co-author with Robert Tibshirani and Jerome Friedman of the book's second edition (2009); the book's site offers a PDF download.3

  • An Introduction to Statistical Learning Published research

    Co-author of the book, with editions using R and Python, and co-teacher with Robert Tibshirani of the companion Statistical Learning online courses.14

Timeline

  1. Completed a Stanford PhD dissertation on principal curves and surfaces.5
  2. Published "Generalized Additive Models" with Robert Tibshirani.5
  3. Co-edited "Statistical Models in S" with John Chambers.5
  4. Published "The Elements of Statistical Learning" with Robert Tibshirani and Jerome Friedman.5
  5. Released the first edition of "An Introduction to Statistical Learning" with applications in R.4
  6. Posted an extended comparison of best subset selection, forward stepwise selection and the lasso.6
  7. Co-authored "Surprises in High-Dimensional Ridgeless Least Squares Interpolation".7
  8. Published the second edition of "An Introduction to Statistical Learning" with R.4
  9. Published the Python edition of "An Introduction to Statistical Learning".4

Other documented roles

Roles the sources document that are not confirmed as current.

  • Member of the technical staff, AT&T Bell Laboratories1

Where they work

Suggest a correction or removal

Profiles cover public professional work only, and each statement cites a source. If something is out of date, missing or wrong, tell us and link a source. People can also ask for their profile to be corrected or removed.

References

8 sources · profile reviewed Oct 21, 2026 · data updated Oct 21, 2026

  1. Trevor Hastie — home pageTrevor Hastie (Stanford University) · Official page · accessed Oct 13, 2026
  2. glmnet: Lasso and Elastic-Net Regularized Generalized Linear Models (CRAN)CRAN · Repository · published Sep 24, 2026 · accessed Oct 21, 2026
  3. The Elements of Statistical Learning: Data Mining, Inference, and Prediction (2nd edition)Trevor Hastie (Stanford University) · Official page · published Feb 2009 · accessed Oct 13, 2026
  4. An Introduction to Statistical LearningAn Introduction to Statistical Learning (authors' site) · Official page · accessed Oct 21, 2026
  5. Trevor J. Hastie — Stanford Department of StatisticsStanford University · Official page · accessed Oct 21, 2026
  6. Extended Comparisons of Best Subset Selection, Forward Stepwise Selection, and the Lasso (arXiv 1707.08692)arXiv · Paper · published Jul 27, 2017 · accessed Oct 21, 2026
  7. Surprises in High-Dimensional Ridgeless Least Squares Interpolation (arXiv 1903.08560)arXiv · Paper · published Mar 19, 2019 · accessed Oct 21, 2026
  8. glmnet documentation siteStanford University (glmnet authors) · Documentation · accessed Oct 13, 2026