H-Index & Metrics Top Publications

H-Index & Metrics

Discipline name H-index Citations Publications World Ranking National Ranking
Computer Science H-index 38 Citations 8,975 86 World Ranking 4908 National Ranking 2417

Research.com Recognitions

Awards & Achievements

2016 - Fellow of Alfred P. Sloan Foundation

Overview

What is he best known for?

The fields of study he is best known for:

  • Statistics
  • Artificial intelligence
  • Machine learning

His primary scientific interests are in Algorithm, Artificial intelligence, Applied mathematics, Singular value decomposition and Mathematical optimization. His study in Algorithm is interdisciplinary in nature, drawing from both Unsupervised learning, Generalization error, Mixture model, Hidden Markov model and VC dimension. Within one scientific family, Daniel Hsu focuses on topics pertaining to Machine learning under Artificial intelligence, and may sometimes address concerns connected to Structure.

His Applied mathematics research is multidisciplinary, incorporating perspectives in Tensor product network, Estimator, Latent variable and Least squares. His research in Singular value decomposition intersects with topics in Symmetric tensor and Combinatorics. Daniel Hsu has researched Mathematical optimization in several fields, including Matrix decomposition, Sparse matrix, Robustness and Matrix completion.

His most cited work include:

  • Tensor decompositions for learning latent variable models (713 citations)
  • Hierarchical sampling for active learning (346 citations)
  • Reconciling modern machine-learning practice and the classical bias-variance trade-off. (340 citations)

What are the main themes of his work throughout his whole career to date?

Daniel Hsu mainly investigates Artificial intelligence, Machine learning, Applied mathematics, Algorithm and Mathematical optimization. Daniel Hsu undertakes interdisciplinary study in the fields of Artificial intelligence and Context through his research. His studies deal with areas such as Classifier and Structure as well as Machine learning.

He combines subjects such as Mixture model, Estimator, Symmetric tensor and Covariance with his study of Applied mathematics. Daniel Hsu has included themes like Generalization, Unsupervised learning, Regret and Hidden Markov model in his Algorithm study. He studied Mathematical optimization and Matrix decomposition that intersect with Singular value decomposition.

He most often published in these fields:

  • Artificial intelligence (28.35%)
  • Machine learning (18.04%)
  • Applied mathematics (16.49%)

What were the highlights of his more recent work (between 2017-2021)?

  • Artificial intelligence (28.35%)
  • Machine learning (18.04%)
  • Combinatorics (12.37%)

In recent papers he was focusing on the following fields of study:

His primary areas of investigation include Artificial intelligence, Machine learning, Combinatorics, Linear regression and Sample size determination. As part of his studies on Artificial intelligence, Daniel Hsu frequently links adjacent subjects like Pattern recognition. He interconnects Classifier, Structure and Class in the investigation of issues within Machine learning.

His Structure study incorporates themes from Active learning and Simple. Combinatorics is closely attributed to Estimator in his research. His Least squares research includes themes of Applied mathematics and Double descent.

Between 2017 and 2021, his most popular works were:

  • Reconciling modern machine-learning practice and the classical bias-variance trade-off. (340 citations)
  • Certified Robustness to Adversarial Examples with Differential Privacy (263 citations)
  • Two models of double descent for weak features (111 citations)

In his most recent research, the most cited papers focused on:

  • Statistics
  • Artificial intelligence
  • Machine learning

Daniel Hsu spends much of his time researching Artificial intelligence, Machine learning, Algorithm, Artificial neural network and Sample size determination. His research integrates issues of Structure and Differential privacy in his study of Artificial intelligence. His research investigates the connection between Machine learning and topics such as Search engine indexing that intersect with issues in Pair distribution function.

The study incorporates disciplines such as Regression and Interpolation in addition to Algorithm. His biological study spans a wide range of topics, including Spurious relationship, Simple and Structure. The concepts of his Sample size determination study are interwoven with issues in Linear regression, Double descent, Norm, Applied mathematics and Least squares.

This overview was generated by a machine learning system which analysed the scientist’s body of work. If you have any feedback, you can contact us here.

Top Publications

Tensor decompositions for learning latent variable models

Animashree Anandkumar;Rong Ge;Daniel Hsu;Sham M. Kakade.
Journal of Machine Learning Research (2014)

906 Citations

Hierarchical sampling for active learning

Sanjoy Dasgupta;Daniel Hsu.
international conference on machine learning (2008)

484 Citations

Reconciling modern machine-learning practice and the classical bias-variance trade-off.

Mikhail Belkin;Daniel Hsu;Siyuan Ma;Soumik Mandal.
Proceedings of the National Academy of Sciences of the United States of America (2019)

469 Citations

Multi-Label Prediction via Compressed Sensing

John Langford;Tong Zhang;Daniel J. Hsu;Sham M Kakade.
neural information processing systems (2009)

464 Citations

Multi-Label Prediction via Compressed Sensing

Daniel Hsu;Sham M. Kakade;John Langford;Tong Zhang.
arXiv: Learning (2009)

417 Citations

A general agnostic active learning algorithm

Sanjoy Dasgupta;Claire Monteleoni;Daniel J. Hsu.
neural information processing systems (2007)

331 Citations

Learning mixtures of spherical gaussians: moment methods and spectral decompositions

Daniel Hsu;Sham M. Kakade.
conference on innovations in theoretical computer science (2013)

318 Citations

Certified Robustness to Adversarial Examples with Differential Privacy

Mathias Lecuyer;Vaggelis Atlidakis;Roxana Geambasu;Daniel Hsu.
ieee symposium on security and privacy (2019)

318 Citations

Taming the Monster: A Fast and Simple Algorithm for Contextual Bandits

Alekh Agarwal;Daniel Hsu;Satyen Kale;John Langford.
international conference on machine learning (2014)

315 Citations

A Method of Moments for Mixture Models and Hidden Markov Models

Animashree Anandkumar;Daniel J. Hsu;Sham M. Kakade.
conference on learning theory (2012)

311 Citations

Profile was last updated on December 6th, 2021.
Research.com Ranking is based on data retrieved from the Microsoft Academic Graph (MAG).
The ranking h-index is inferred from publications deemed to belong to the considered discipline.

If you think any of the details on this page are incorrect, let us know.

Contact us

Top Scientists Citing Daniel Hsu

Anima Anandkumar

Anima Anandkumar

California Institute of Technology

Publications: 40

Martin J. Wainwright

Martin J. Wainwright

University of California, Berkeley

Publications: 40

John Langford

John Langford

Microsoft (United States)

Publications: 39

Alekh Agarwal

Alekh Agarwal

Microsoft (United States)

Publications: 33

Kamalika Chaudhuri

Kamalika Chaudhuri

University of California, San Diego

Publications: 30

Prateek Jain

Prateek Jain

Microsoft (India)

Publications: 30

Namrata Vaswani

Namrata Vaswani

Iowa State University

Publications: 29

Michael I. Jordan

Michael I. Jordan

University of California, Berkeley

Publications: 29

Ankur Moitra

Ankur Moitra

MIT

Publications: 29

Anima Anandkumar

Anima Anandkumar

Nvidia (United Kingdom)

Publications: 28

Maria-Florina Balcan

Maria-Florina Balcan

Carnegie Mellon University

Publications: 27

Sham M. Kakade

Sham M. Kakade

University of Washington

Publications: 27

Sujay Sanghavi

Sujay Sanghavi

The University of Texas at Austin

Publications: 24

Robert E. Schapire

Robert E. Schapire

Microsoft (United States)

Publications: 24

Geoffrey J. Gordon

Geoffrey J. Gordon

Carnegie Mellon University

Publications: 22

Something went wrong. Please try again later.