2.2k citations
- IBM (United States)US73 papers
- Stanford UniversityUS62 papers
- IBM Research - Thomas J. Watson Research CenterUS42 papers
- University of California, BerkeleyUS22 papers
- IBM Research - ZurichCH21 papers
- California Institute of TechnologyUS20 papers
- École Polytechnique Fédérale de LausanneCH15 papers
- Massachusetts Institute of TechnologyUS14 papers
- Max Planck Institute of Microstructure PhysicsDE13 papers
- ETH ZurichCH10 papers
- Princeton UniversityUS10 papers
- SLAC National Accelerator LaboratoryUS10 papers
4 papers · 2 filters
Strategic Classification
Moritz Hardt, Nimrod Megiddo, Christos Papadimitriou +1
Machine learning relies on the assumption that unseen test instances of a classification problem follow the same distribution as observed training data. However, this principle can…
Generalization in Adaptive Data Analysis and Holdout Reuse
Cynthia Dwork, Vitaly Feldman, Moritz Hardt +3
Overfitting is the bane of data analysts, even when data are plentiful. Formal approaches to understanding this problem focus on statistical inference and generalization of individ…
Communication Efficient Distributed Kernel Principal Component Analysis
Maria-Florina Balcan, Yingyu Liang, Le Song +2
Kernel Principal Component Analysis (KPCA) is a key machine learning algorithm for extracting nonlinear features from data. In the presence of a large volume of high dimensional da…
Deep Learning with Limited Numerical Precision
Suyog Gupta, Ankur Agrawal, Kailash Gopalakrishnan +1
Training of large-scale deep neural networks is often constrained by the available computational resources. We study the effect of limited precision data representation and computa…