H-Index & Metrics Top Publications

H-Index & Metrics

Discipline name H-index Citations Publications World Ranking National Ranking
Computer Science H-index 73 Citations 24,638 223 World Ranking 672 National Ranking 408

Overview

What is he best known for?

The fields of study he is best known for:

  • Artificial intelligence
  • Statistics
  • Algorithm

Mehryar Mohri mainly focuses on Algorithm, Theoretical computer science, Artificial intelligence, Mathematical optimization and Automaton. His studies deal with areas such as Discrete mathematics, Kernel method, Kernel, Distribution and Simple as well as Algorithm. His Theoretical computer science research is multidisciplinary, relying on both Finite-state machine, Programming language, String, Key and Natural language.

The concepts of his Artificial intelligence study are interwoven with issues in Ranking, Machine learning, Natural language processing and Pattern recognition. His Mathematical optimization study incorporates themes from Regularization, Training set and Regression, Regression problems. The study incorporates disciplines such as Representation, Speech processing and Minification in addition to Automaton.

His most cited work include:

  • Foundations of Machine Learning (1022 citations)
  • Finite-state transducers in language and speech processing (844 citations)
  • Weighted finite-state transducers in speech recognition (788 citations)

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

Mehryar Mohri mostly deals with Algorithm, Artificial intelligence, Theoretical computer science, Automaton and Discrete mathematics. His Algorithm research includes elements of Semiring and Support vector machine. His studies examine the connections between Artificial intelligence and genetics, as well as such issues in Speech recognition, with regards to Rule-based machine translation.

His Theoretical computer science study combines topics in areas such as Context, Key, Series and Regret. His Automaton research incorporates elements of Pseudocode, String and Minification. His Discrete mathematics research is multidisciplinary, incorporating perspectives in Generalization, Rademacher complexity and Combinatorics.

He most often published in these fields:

  • Algorithm (41.92%)
  • Artificial intelligence (24.25%)
  • Theoretical computer science (20.96%)

What were the highlights of his more recent work (between 2015-2021)?

  • Algorithm (41.92%)
  • Theoretical computer science (20.96%)
  • Regret (8.68%)

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

Mehryar Mohri mainly investigates Algorithm, Theoretical computer science, Regret, Artificial intelligence and Machine learning. His work blends Algorithm and Multiple source studies together. His Theoretical computer science study also includes fields such as

  • Optimization problem, which have a strong connection to Inference,
  • Structured prediction and related Minification.

His study in Artificial intelligence is interdisciplinary in nature, drawing from both Structure and Generalization. His work on Model selection as part of general Machine learning research is frequently linked to Online learning, Special case and Exploit, bridging the gap between disciplines. His work deals with themes such as Automaton, Computation, Online algorithm and Rademacher complexity, which intersect with Key.

Between 2015 and 2021, his most popular works were:

  • Advances and Open Problems in Federated Learning (571 citations)
  • Agnostic federated learning (178 citations)
  • SCAFFOLD: Stochastic Controlled Averaging for On-Device Federated Learning. (81 citations)

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

  • Artificial intelligence
  • Statistics
  • Machine learning

His scientific interests lie mostly in Artificial intelligence, Machine learning, Theoretical computer science, Mathematical optimization and Federated learning. Artificial intelligence is frequently linked to Structure in his study. His Machine learning research incorporates themes from Classifier, Personalization and Class.

As part of one scientific family, Mehryar Mohri deals mainly with the area of Theoretical computer science, narrowing it down to issues related to the Optimization problem, and often Stochastic algorithms, Contrast, Inference and Set. Mehryar Mohri works mostly in the field of Mathematical optimization, limiting it down to concerns involving Simplicity and, occasionally, Distributed computing. Mehryar Mohri connects Function with Algorithm in his research.

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

Foundations of Machine Learning

Mehryar Mohri;Afshin Rostamizadeh;Afshin Rostamizadeh;Ameet Talwalkar;Ameet Talwalkar.
(2012)

3028 Citations

Finite-state transducers in language and speech processing

Mehryar Mohri.
Computational Linguistics (1997)

1297 Citations

Weighted finite-state transducers in speech recognition

Mehryar Mohri;Fernando Pereira;Michael Riley.
Computer Speech & Language (2002)

1175 Citations

OpenFst: a general and efficient weighted finite-state transducer library

Cyril Allauzen;Michael Riley;Johan Schalkwyk;Wojciech Skut.
international conference on implementation and application of automata (2007)

725 Citations

AUC Optimization vs. Error Rate Minimization

Corinna Cortes;Mehryar Mohri.
neural information processing systems (2003)

667 Citations

Advances and Open Problems in Federated Learning

Peter Kairouz;H. Brendan McMahan;Brendan Avent;Aurélien Bellet.
Foundations and Trends® in Machine Learning (2021)

603 Citations

Advances and Open Problems in Federated Learning

Peter Kairouz;H. Brendan McMahan;Brendan Avent;Aurélien Bellet.
arXiv: Learning (2019)

585 Citations

Multi-armed bandit algorithms and empirical evaluation

Joannès Vermorel;Mehryar Mohri.
european conference on machine learning (2005)

575 Citations

Domain adaptation: Learning bounds and algorithms

Yishay Mansour;Mehryar Mohri;Afshin Rostamizadeh.
conference on learning theory (2009)

402 Citations

Domain Adaptation with Multiple Sources

Yishay Mansour;Mehryar Mohri;Afshin Rostamizadeh.
neural information processing systems (2008)

378 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 Mehryar Mohri

Hermann Ney

Hermann Ney

RWTH Aachen University

Publications: 48

Murat Saraclar

Murat Saraclar

Boğaziçi University

Publications: 43

Masashi Sugiyama

Masashi Sugiyama

University of Tokyo

Publications: 42

William Byrne

William Byrne

University of Cambridge

Publications: 40

Zhi-Hua Zhou

Zhi-Hua Zhou

Nanjing University

Publications: 32

Rong Jin

Rong Jin

Alibaba Group (China)

Publications: 30

Mark J. F. Gales

Mark J. F. Gales

University of Cambridge

Publications: 30

Dacheng Tao

Dacheng Tao

University of Sydney

Publications: 29

Thomas R. Gruber

Thomas R. Gruber

Apple (United States)

Publications: 28

Isabel Trancoso

Isabel Trancoso

Instituto Superior Técnico

Publications: 28

Michael Riley

Michael Riley

Google (United States)

Publications: 28

Orna Kupferman

Orna Kupferman

Hebrew University of Jerusalem

Publications: 26

Michael I. Jordan

Michael I. Jordan

University of California, Berkeley

Publications: 26

Brian Roark

Brian Roark

Google (United States)

Publications: 25

Jason Eisner

Jason Eisner

Johns Hopkins University

Publications: 25

Something went wrong. Please try again later.