H-Index & Metrics Top Publications

H-Index & Metrics

Discipline name H-index Citations Publications World Ranking National Ranking
Engineering and Technology H-index 69 Citations 19,881 147 World Ranking 305 National Ranking 144

Overview

What is he best known for?

The fields of study he is best known for:

  • Artificial intelligence
  • Statistics
  • Machine learning

His primary areas of investigation include Mathematical optimization, Algorithm, Regret, Reinforcement learning and Artificial intelligence. Sham M. Kakade brings together Mathematical optimization and System identification to produce work in his papers. His Algorithm research incorporates themes from Mixture model, Unsupervised learning, Implicit function and Hidden Markov model.

The various areas that Sham M. Kakade examines in his Regret study include Curse of dimensionality, Code, Function, Upper and lower bounds and Compressed sensing. His study in Reinforcement learning is interdisciplinary in nature, drawing from both Robot and State space. Sham M. Kakade combines subjects such as Machine learning and Pattern recognition with his study of Artificial intelligence.

His most cited work include:

  • Gaussian Process Optimization in the Bandit Setting: No Regret and Experimental Design (877 citations)
  • Tensor decompositions for learning latent variable models (713 citations)
  • Cover trees for nearest neighbor (677 citations)

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

His scientific interests lie mostly in Mathematical optimization, Algorithm, Artificial intelligence, Applied mathematics and Reinforcement learning. His biological study spans a wide range of topics, including Stochastic gradient descent, Gradient descent, Simple, Markov decision process and Regret. The concepts of his Algorithm study are interwoven with issues in Mixture model, Matrix, Unsupervised learning and Hidden Markov model.

His Artificial intelligence study incorporates themes from Machine learning and Pattern recognition. His Applied mathematics study integrates concerns from other disciplines, such as Regularization, Covariance, Convexity, Estimator and Generalization. His work deals with themes such as Parameterized complexity, Supervised learning, Sample, Polynomial and Function approximation, which intersect with Reinforcement learning.

He most often published in these fields:

  • Mathematical optimization (31.43%)
  • Algorithm (18.21%)
  • Artificial intelligence (15.71%)

What were the highlights of his more recent work (between 2018-2021)?

  • Mathematical optimization (31.43%)
  • Reinforcement learning (12.50%)
  • Applied mathematics (15.00%)

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

Sham M. Kakade spends much of his time researching Mathematical optimization, Reinforcement learning, Applied mathematics, Algorithm and Markov decision process. He interconnects Sampling, Control and Sample size determination in the investigation of issues within Mathematical optimization. He has researched Reinforcement learning in several fields, including Upper and lower bounds, Sample, Function approximation and Curse of dimensionality.

The study incorporates disciplines such as Regularization, Stochastic gradient descent and Regret in addition to Applied mathematics. His Algorithm study combines topics from a wide range of disciplines, such as Entropy, Generative grammar and Pruning. His work in Markov decision process covers topics such as State space which are related to areas like Generative model.

Between 2018 and 2021, his most popular works were:

  • Meta-Learning with Implicit Gradients (144 citations)
  • PACT: Privacy Sensitive Protocols and Mechanisms for Mobile Contact Tracing (85 citations)
  • Optimality and Approximation with Policy Gradient Methods in Markov Decision Processes (81 citations)

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

  • Artificial intelligence
  • Statistics
  • Machine learning

The scientist’s investigation covers issues in Regret, Mathematical optimization, Artificial intelligence, Linear dynamical system and Applied mathematics. His work on Intelligent decision support system expands to the thematically related Regret. His research brings together the fields of Markov decision process and Mathematical optimization.

His Artificial intelligence research includes themes of Contrast and Sample. His studies examine the connections between Linear dynamical system and genetics, as well as such issues in Control, with regards to Statistical noise. His work carried out in the field of Applied mathematics brings together such families of science as Measure, Double descent and Convexity.

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

Gaussian Process Optimization in the Bandit Setting: No Regret and Experimental Design

Niranjan Srinivas;Andreas Krause;Matthias Seeger;Sham M. Kakade.
international conference on machine learning (2010)

1387 Citations

Cover trees for nearest neighbor

Alina Beygelzimer;Sham Kakade;John Langford.
international conference on machine learning (2006)

938 Citations

Tensor decompositions for learning latent variable models

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

906 Citations

A Natural Policy Gradient

Sham M Kakade.
neural information processing systems (2001)

870 Citations

Opponent interactions between serotonin and dopamine

Nathaniel D. Daw;Sham Kakade;Peter Dayan.
Neural Networks (2002)

840 Citations

Multi-view clustering via canonical correlation analysis

Kamalika Chaudhuri;Sham M. Kakade;Karen Livescu;Karthik Sridharan.
international conference on machine learning (2009)

743 Citations

Stochastic Linear Optimization Under Bandit Feedback

Varsha Dani;Thomas P Hayes;Sham M Kakade.
conference on learning theory (2008)

589 Citations

On the Sample Complexity of Reinforcement Learning

Sham Machandranath Kakade.
Doctoral thesis, UCL (University College London). (2003)

536 Citations

Approximately Optimal Approximate Reinforcement Learning

Sham Kakade;John Langford.
international conference on machine learning (2002)

532 Citations

Learning and selective attention.

P Dayan;S Kakade;P R Montague.
Nature Neuroscience (2000)

485 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 Sham M. Kakade

Andreas Krause

Andreas Krause

ETH Zurich

Publications: 70

Csaba Szepesvári

Csaba Szepesvári

University of Alberta

Publications: 57

Shie Mannor

Shie Mannor

Technion – Israel Institute of Technology

Publications: 55

Raymond J. Dolan

Raymond J. Dolan

University College London

Publications: 53

Jan Peters

Jan Peters

TU Darmstadt

Publications: 50

Dacheng Tao

Dacheng Tao

University of Sydney

Publications: 48

Michael I. Jordan

Michael I. Jordan

University of California, Berkeley

Publications: 47

Elad Hazan

Elad Hazan

Princeton University

Publications: 46

John Langford

John Langford

Microsoft (United States)

Publications: 46

Emrah Düzel

Emrah Düzel

German Center for Neurodegenerative Diseases

Publications: 44

Nathaniel D. Daw

Nathaniel D. Daw

Princeton University

Publications: 43

Rémi Munos

Rémi Munos

DeepMind (United Kingdom)

Publications: 43

Anima Anandkumar

Anima Anandkumar

California Institute of Technology

Publications: 42

Geoffrey Schoenbaum

Geoffrey Schoenbaum

National Institute on Drug Abuse

Publications: 40

Svetha Venkatesh

Svetha Venkatesh

Deakin University

Publications: 40

Something went wrong. Please try again later.