T
Trevor Hastie
Researcher at Stanford University
Publications - 428
Citations - 230646
Trevor Hastie is an academic researcher from Stanford University. The author has contributed to research in topics: Lasso (statistics) & Feature selection. The author has an hindex of 124, co-authored 412 publications receiving 202592 citations. Previous affiliations of Trevor Hastie include University of Waterloo & University of Toronto.
Papers
More filters
Proceedings Article
Learning Prototype Models for Tangent Distance
Trevor Hastie,Patrice Y. Simard +1 more
TL;DR: Rich models for representing large subsets of the prototypes are developed either used singly per class, or as basic building blocks in conjunction with the K-means clustering algorithm.
Journal Article
Local case-control sampling: Efficient subsampling in imbalanced data sets
William Fithian,Trevor Hastie +1 more
TL;DR: This work proposes a method for subsampling efficiently for logistic regression by adjusting the class balance locally in feature space via an accept-reject scheme, and shows that this method can substantially outperform standard case-control subsampled.
Book ChapterDOI
Nonlinear Estimators and Tail Bounds for Dimension Reduction in l 1 Using Cauchy Random Projections
TL;DR: In this paper, the authors study three types of nonlinear estimators: the sample median estimators, the geometric mean estimators and the maximum likelihood estimators (MLE), and establish that k = O(log n/e2) suffices with the constants explicitly given.
Journal ArticleDOI
Modeling and predicting osteoarthritis progression: data from the osteoarthritis initiative.
TL;DR: Statistical models for characterizing and predicting OA progression promise to improve clinical trial design and OA prevention efforts in the future.
Patent
Method for signature verification
TL;DR: In this article, a method and apparatus are described for verifying handwritten, human signatures, and for permitting access to a system if such a signature is accepted, and a signature acceptance criterion that refers to the dynamic and shape mismatch values is defined.