World's Best Scientists 2026 revealed!

D-Index & Metrics

Computer Science

D-Index
70
Citations
26319
World Ranking
1840
National Ranking
936

Overview

Nathan Srebro is affiliated with the Toyota Technological Institute at Chicago in the United States. Their research primarily intersects the field of Computer Science, with a strong emphasis on subfields including Artificial Intelligence, Computational Mechanics, Statistics and Probability, Computer Vision and Pattern Recognition, and Electrical and Electronic Engineering.

The main topics in Nathan Srebro's research contributions cover a variety of areas related to machine learning and optimization. These include:

  • Machine Learning and Algorithms
  • Stochastic Gradient Optimization Techniques
  • Sparse and Compressive Sensing Techniques
  • Domain Adaptation and Few-Shot Learning
  • Adversarial Robustness in Machine Learning
  • Machine Learning and Data Classification
  • Neural Networks and Applications

Nathan Srebro has coauthored numerous publications with frequent collaborators such as Gal Vardi, Blake Woodworth, Ohad Shamir, Daniel Soudry, and Lijia Zhou. These collaborators have appeared repeatedly in Srebro's work, indicating ongoing academic partnerships.

Their publication record includes a range of papers across several venues. Some significant recent papers are:

  • Lower bounds for non-convex stochastic optimization, 2022, Mathematical Programming
  • Is Local SGD Better than Minibatch SGD?, 2020, arXiv (Cornell University)
  • Minibatch vs Local SGD for Heterogeneous Distributed Learning, 2020, arXiv (Cornell University)
  • Does Invariant Risk Minimization Capture Invariance?, 2021, arXiv (Cornell University)
  • Fair Learning with Private Demographic Data, 2020, arXiv (Cornell University)

The majority of Nathan Srebro's work has been disseminated through arXiv (Cornell University), accounting for 61 publications. Other venues include Mathematical Programming, the Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, the ACM / IMS Journal of Data Science, and the Journal of Statistical Mechanics Theory and Experiment, reflecting a diverse range of publication outlets.

Best Publications

  • Pegasos: primal estimated sub-gradient solver for SVM

    Shai Shalev-Shwartz;Yoram Singer;Nathan Srebro;Andrew Cotter

  • Equality of opportunity in supervised learning

    Moritz Hardt;Eric Price;Nathan Srebro

  • Pegasos: Primal Estimated sub-GrAdient SOlver for SVM

    Shai Shalev-Shwartz;Yoram Singer;Nathan Srebro

  • Maximum-Margin Matrix Factorization

    Nathan Srebro;Jason Rennie;Tommi S. Jaakkola

  • Fast maximum margin matrix factorization for collaborative prediction

    Jasson D. M. Rennie;Nathan Srebro

  • Exploring Generalization in Deep Learning

    Behnam Neyshabur;Srinadh Bhojanapalli;David McAllester;Nathan Srebro

  • Weighted low-rank approximations

    Nathan Srebro;Tommi Jaakkola

  • The Marginal Value of Adaptive Gradient Methods in Machine Learning

    Ashia C. Wilson;Rebecca Roelofs;Mitchell Stern;Nathan Srebro

  • Communication-Efficient Distributed Optimization using an Approximate Newton-type Method

    Ohad Shamir;Nati Srebro;Tong Zhang

  • The implicit bias of gradient descent on separable data

    Daniel Soudry;Elad Hoffer;Mor Shpigel Nacson;Suriya Gunasekar

  • Rank, trace-norm and max-norm

    Nathan Srebro;Adi Shraibman

  • Norm-Based Capacity Control in Neural Networks

    Behnam Neyshabur;Ryota Tomioka;Nathan Srebro

  • In Search of the Real Inductive Bias: On the Role of Implicit Regularization in Deep Learning

    Behnam Neyshabur;Ryota Tomioka;Nathan Srebro

  • Learnability, Stability and Uniform Convergence

    Shai Shalev-Shwartz;Ohad Shamir;Nathan Srebro;Karthik Sridharan

  • Uncovering shared structures in multiclass classification

    Yonatan Amit;Michael Fink;Nathan Srebro;Shimon Ullman

  • A PAC-Bayesian Approach to Spectrally-Normalized Margin Bounds for Neural Networks

    Behnam Neyshabur;Srinadh Bhojanapalli;Nathan Srebro

  • SVM optimization: inverse dependence on training set size

    Shai Shalev-Shwartz;Nathan Srebro

  • Learning with matrix factorizations

    Nathan Srebro;Tommi S. Jaakkola

  • Global optimality of local search for low rank matrix recovery

    Srinadh Bhojanapalli;Behnam Neyshabur;Nathan Srebro

  • Towards Understanding the Role of Over-Parametrization in Generalization of Neural Networks

    Behnam Neyshabur;Zhiyuan Li;Srinadh Bhojanapalli;Yann LeCun

  • Stochastic Gradient Descent, Weighted Sampling, and the Randomized Kaczmarz algorithm

    Deanna Needell;Nathan Srebro;Rachel Ward

  • The Implicit Bias of Gradient Descent on Separable Data

    Daniel Soudry;Elad Hoffer;Mor Shpigel Nacson;Nathan Srebro

  • The Implicit Bias of Gradient Descent on Separable Data

    Daniel Soudry;Elad Hoffer;Nathan Srebro

Frequent Co-Authors

Daniel Soudry
Daniel Soudry Technion – Israel Institute of Technology
Karthik Sridharan
Karthik Sridharan Cornell University
Ohad Shamir
Ohad Shamir Weizmann Institute of Science
Jason D. Lee
Jason D. Lee Princeton University
Ruslan Salakhutdinov
Ruslan Salakhutdinov Carnegie Mellon University
Shai Shalev-Shwartz
Shai Shalev-Shwartz Hebrew University of Jerusalem
Tong Zhang
Tong Zhang University of Illinois at Urbana-Champaign
Ryota Tomioka
Ryota Tomioka Microsoft (United States)
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

Exploring Computer Science in the USA opens doors to a wide range of educational options and career paths. If you’re aiming to position yourself for career advancement or specialization, you might consider pursuing a master’s degree. To help choose the right program, it’s wise to review trends and guidance on what masters program should i do based on job market demand and personal interests.

If you’re just starting out, an online associate's degree can be an accessible way to gain core technical skills and enter the workforce quickly. This path is ideal for those needing flexibility or seeking a cost-effective introduction to computer science.

Affordability and accessibility are crucial. Many students compare affordable online colleges to find options that suit their financial situation without compromising quality. Additionally, if your academic record isn’t perfect, you’ll still find online colleges that accept low gpa, making higher education and tech careers more inclusive for everyone.

Best Scientists Citing Nathan Srebro

Trending Scientists

Recently Published Articles