World's Best Scientists 2026 revealed!

D-Index & Metrics

Computer Science

D-Index
87
Citations
28939
World Ranking
728
National Ranking
384

Overview

Sham M. Kakade is affiliated with Harvard University in the United States and has contributed extensively to the field of computer science, with a particular focus on artificial intelligence.

The primary fields of study covered in their research include:

  • Computer Science

Their work spans several subfields, notably:

  • Artificial Intelligence
  • Management Science and Operations Research
  • Computational Mechanics
  • Computer Vision and Pattern Recognition
  • Computer Networks and Communications

Kakade's research topics highlight areas such as:

  • Reinforcement Learning in Robotics
  • Domain Adaptation and Few-Shot Learning
  • Stochastic Gradient Optimization Techniques
  • Advanced Bandit Algorithms Research
  • Machine Learning and Algorithms
  • Neural Networks and Applications
  • Sparse and Compressive Sensing Techniques

Selected recent papers include:

  • "Robust Aggregation for Federated Learning", 2022, IEEE Transactions on Signal Processing
  • "Soft Threshold Weight Reparameterization for Learnable Sparsity", 2020, arXiv (Cornell University)
  • "On Nonconvex Optimization for Machine Learning", 2021, Journal of the ACM
  • "Few-Shot Learning via Learning the Representation, Provably", 2020, arXiv (Cornell University)
  • "Optimal Regularization Can Mitigate Double Descent", 2020, arXiv (Cornell University)

The frequent publication venues where Kakade's work appears are:

  • arXiv (Cornell University)
  • IEEE Transactions on Signal Processing
  • Journal of the ACM
  • Singapore Management University Institutional Knowledge (InK) (Singapore Management University)
  • Journal of Real Estate Construction & Management

Among frequent coauthors collaborating with Kakade are:

  • Nikhil Vyas
  • Depen Morwani
  • Jason D. Lee
  • Akshay Krishnamurthy
  • Eran Malach

Best Publications

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

    Niranjan Srinivas;Andreas Krause;Matthias Seeger;Sham M. Kakade

  • Tensor decompositions for learning latent variable models

    Animashree Anandkumar;Rong Ge;Daniel Hsu;Sham M. Kakade

  • A Natural Policy Gradient

    Sham M Kakade

  • Cover trees for nearest neighbor

    Alina Beygelzimer;Sham Kakade;John Langford

  • Opponent interactions between serotonin and dopamine

    Nathaniel D. Daw;Sham Kakade;Peter Dayan

  • Information-Theoretic Regret Bounds for Gaussian Process Optimization in the Bandit Setting

    N. Srinivas;A. Krause;S. M. Kakade;M. Seeger

  • Multi-view clustering via canonical correlation analysis

    Kamalika Chaudhuri;Sham M. Kakade;Karen Livescu;Karthik Sridharan

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

    Niranjan Srinivas;Andreas Krause;Sham M. Kakade;Matthias Seeger

  • Approximately Optimal Approximate Reinforcement Learning

    Sham Kakade;John Langford

  • Stochastic Linear Optimization Under Bandit Feedback

    Varsha Dani;Thomas P Hayes;Sham M Kakade

  • How to escape saddle points efficiently

    Chi Jin;Rong Ge;Praneeth Netrapalli;Sham M. Kakade

  • Learning and selective attention.

    P Dayan;S Kakade;P R Montague

  • On the Sample Complexity of Reinforcement Learning

    Sham Machandranath Kakade

  • Dopamine: generalization and bonuses

    Sham Kakade;Peter Dayan

  • A spectral algorithm for learning Hidden Markov Models

    Daniel Hsu;Sham M. Kakade;Tong Zhang

  • Multi-Label Prediction via Compressed Sensing

    John Langford;Tong Zhang;Daniel J. Hsu;Sham M Kakade

  • Meta-Learning with Implicit Gradients

    Aravind Rajeswaran;Chelsea Finn;Sham M. Kakade;Sergey Levine

  • Multi-Label Prediction via Compressed Sensing

    Daniel Hsu;Sham M. Kakade;John Langford;Tong Zhang

  • A tail inequality for quadratic forms of subgaussian random vectors

    Daniel J. Hsu;Sham M. Kakade;Tong Zhang

  • Learning mixtures of spherical gaussians: moment methods and spectral decompositions

    Daniel Hsu;Sham M. Kakade

  • Global Convergence of Policy Gradient Methods for the Linear Quadratic Regulator.

    Maryam Fazel;Rong Ge;Sham M. Kakade;Mehran Mesbahi

  • Robust Aggregation for Federated Learning

    Krishna Pillutla;Sham M. Kakade;Zaid Harchaoui

Frequent Co-Authors

Daniel Hsu
Daniel Hsu Columbia University
Praneeth Netrapalli
Praneeth Netrapalli Google (United States)
Rong Ge
Rong Ge Duke University
Dean P. Foster
Dean P. Foster Amazon (United States)
Aaron Sidford
Aaron Sidford Stanford University
Prateek Jain
Prateek Jain Google (United States)
Tong Zhang
Tong Zhang University of Illinois at Urbana-Champaign
Alekh Agarwal
Alekh Agarwal Google (United States)
Anima Anandkumar
Anima Anandkumar Nvidia (United Kingdom)
Ambuj Tewari
Ambuj Tewari University of Michigan–Ann Arbor

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

Report an issue

We appreciate your kind effort to assist us to improve this page, it would be helpful providing us with as much detail as possible in the text box below:

Related Online Degrees & Career Pathways

Studying Computer Science in the USA opens up a variety of flexible online education options for students at every career stage. For those looking to launch a tech career quickly, certifications that pay well can provide valuable credentials and fast-track entry into in-demand technical jobs, often without a four-year degree.

If you're aiming to advance your education, choosing what masters program should I do can be key to long-term career growth. For busy professionals, the fastest masters degree online options offer accelerated pathways to higher qualifications and new job opportunities in computer science and related fields.

Alternatively, those seeking a more foundational credential can consider an associates degree online in computer science or IT. This is a great way to build technical skills and access entry-level jobs, while keeping future options open for further study or specialization.

No matter which pathway you choose, online degrees and certifications can make computer science education more accessible and aligned with your career goals.

Best Scientists Citing Sham M. Kakade

Trending Scientists

Recently Published Articles