World's Best Scientists 2026 revealed!

D-Index & Metrics

Computer Science

D-Index
50
Citations
33529
World Ranking
5456
National Ranking
2488

Research.com Recognitions

  • 2018 - SPIE Fellow

Overview

Mikhail Belkin is affiliated with the University of California, San Diego in the United States. Their research spans primarily the fields of Computer Science and Engineering, with a particular focus on several key subfields including Artificial Intelligence, Electrical and Electronic Engineering, Computer Vision and Pattern Recognition, Computational Mechanics, and Statistics and Probability.

The scientist's work covers critical topics such as Neural Networks and Applications, Advanced Photonic Communication Systems, Stochastic Gradient Optimization Techniques, Machine Learning and Data Classification, Optical Network Technologies, Sparse and Compressive Sensing Techniques, and Model Reduction and Neural Networks.

Among Mikhail Belkin's recent publications are:

  • Loss landscapes and optimization in over-parameterized non-linear systems and neural networks (2022, Applied and Computational Harmonic Analysis)
  • Evaluation of Neural Architectures Trained with Square Loss vs Cross-Entropy in Classification Tasks (2020, arXiv (Cornell University))
  • Classification vs regression in overparameterized regimes: Does the loss function matter? (2020, arXiv (Cornell University))
  • Mechanism for feature learning in neural networks and backpropagation-free machine learning models (2024, Science)
  • On the linearity of large non-linear models: when and why the tangent kernel is constant (2020, arXiv (Cornell University))

Frequent co-authors collaborating with Mikhail Belkin include Adityanarayanan Radhakrishnan, Parthe Pandit, А. С. Сигов, Daniel Beaglehole, and Dmitriy Fofanov.

The most common publication venues for their work include:

  • arXiv (Cornell University)
  • Proceedings of the National Academy of Sciences
  • Nano- i Mikrosistemnaya Tehnika
  • SIAM Journal on Mathematics of Data Science
  • Applied and Computational Harmonic Analysis

Mikhail Belkin has been recognized as a SPIE Fellow since 2018, reflecting involvement in fields overlapping optics and photonics among other areas.

Best Publications

  • Laplacian Eigenmaps for dimensionality reduction and data representation

    Mikhail Belkin;Partha Niyogi

  • Laplacian Eigenmaps and Spectral Techniques for Embedding and Clustering

    Mikhail Belkin;Partha Niyogi

  • Manifold Regularization: A Geometric Framework for Learning from Labeled and Unlabeled Examples

    Mikhail Belkin;Partha Niyogi;Vikas Sindhwani

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

    Mikhail Belkin;Daniel Hsu;Siyuan Ma;Soumik Mandal

  • Semi-Supervised Learning on Riemannian Manifolds

    Mikhail Belkin;Partha Niyogi

  • Towards a theoretical foundation for Laplacian-based manifold methods

    Mikhail Belkin;Partha Niyogi

  • Regularization and Semi-supervised Learning on Large Graphs

    Mikhail Belkin;Irina Matveeva;Partha Niyogi

  • Consistency of spectral clustering

    U von Luxburg;M Belkin;O Bousquet

  • Beyond the point cloud: from transductive to semi-supervised learning

    Vikas Sindhwani;Partha Niyogi;Mikhail Belkin

  • A Co-Regularization Approach to Semi-supervised Learning with Multiple Views

    Vikas Sindhwani;Partha Niyogi;Mikhail Belkin

  • Laplacian Support Vector Machines Trained in the Primal

    Stefano Melacci;Mikhail Belkin

  • Convergence of Laplacian Eigenmaps

    Mikhail Belkin;Partha Niyogi

  • Two Models of Double Descent for Weak Features

    Mikhail Belkin;Daniel Hsu;Ji Xu

  • Semi-Supervised Learning

    Xueyuan Zhou;Mikhail Belkin

  • Consistency of spectral clustering

    Ulrike von Luxburg;Mikhail Belkin;Olivier Bousquet

  • Discrete laplace operator on meshed surfaces

    Mikhail Belkin;Jian Sun;Yusu Wang

  • Polynomial Learning of Distribution Families

    Mikhail Belkin;Kaushik Sinha

  • Loss landscapes and optimization in over-parameterized non-linear systems and neural networks

    Unknown

  • To understand deep learning we need to understand kernel learning

    Mikhail Belkin;Siyuan Ma;Soumik Mandal

  • On Learning with Integral Operators

    Lorenzo Rosasco;Mikhail Belkin;Ernesto De Vito

  • Using manifold structure for partially labelled classification

    Mikhail Belkin;Partha Niyogi

Frequent Co-Authors

Partha Niyogi
Partha Niyogi University of Chicago
Yusu Wang
Yusu Wang University of California, San Diego
Daniel Hsu
Daniel Hsu Columbia University
Olivier Bousquet
Olivier Bousquet Google (United States)
Bin Yu
Bin Yu University of California, Berkeley
Vikas Sindhwani
Vikas Sindhwani Google (United States)
Ulrike von Luxburg
Ulrike von Luxburg University of Tübingen
Dong Xuan
Dong Xuan The Ohio State University

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

Exploring Computer Science in the USA opens the door to numerous related degrees and career paths—many of which can be accessed online. For those drawn to data analysis, pursuing a data scientist degree is a popular option. These programs focus on real-world problem-solving skills and are often structured for flexibility and affordability.

If your interests lean toward electronics and technology, consider the online electrical engineering career outcomes. These pathways offer strong earning potential and diverse job prospects in industries such as robotics, energy, and telecommunications.

Looking for fast credentials? There are also certificate programs that pay well. These certifications can boost your resume in a short time and lead to lucrative roles in IT, cybersecurity, and more.

For those seeking advanced qualifications without a long commitment, the quickest cheapest masters degree options let you upgrade your credentials efficiently—saving both time and money as you advance your career.

Best Scientists Citing Mikhail Belkin

Trending Scientists

Recently Published Articles