World's Best Scientists 2026 revealed!

D-Index & Metrics

Computer Science

D-Index
86
Citations
46937
World Ranking
751
National Ranking
398

Research.com Recognitions

  • 2018 - ACM Fellow For contributions to the theory of machine learning

Overview

Peter L. Bartlett is affiliated with the University of California, Berkeley in the United States. Their work primarily focuses on computer science, with significant contributions to artificial intelligence, statistics and probability, management science and operations research, computational mechanics, and computer vision and pattern recognition.

The main subjects of their research encompass stochastic gradient optimization techniques, advanced bandit algorithms research, machine learning and algorithms, statistical methods and inference, sparse and compressive sensing techniques, reinforcement learning in robotics, and domain adaptation and few-shot learning.

Frequent coauthors include Michael I. Jordan, Aldo Pacchiano, Philip M. Long, Niladri S. Chatterji, and Martin J. Wainwright, with collaborations spanning multiple publications.

The scientist has published extensively, with key publication venues including arXiv (Cornell University), Bernoulli, Proceedings of the National Academy of Sciences, Acta Numerica, and the Journal of the American Statistical Association.

  • Self-Distillation Amplifies Regularization in Hilbert Space, 2020, arXiv (Cornell University)
  • Reinforcement Learning in POMDP's via Direct Gradient Ascent, 2025, arXiv (Cornell University)
  • Benign overfitting in ridge regression, 2020, arXiv (Cornell University)
  • Benign overfitting in linear regression, 2020, Proceedings of the National Academy of Sciences
  • Is there an analog of Nesterov acceleration for gradient-based MCMC?, 2021, Bernoulli

Peter L. Bartlett received the ACM Fellow award in 2018 for contributions to the theory of machine learning.

Best Publications

  • New Support Vector Algorithms

    Bernhard Schölkopf;Alex J. Smola;Robert C. Williamson;Peter L. Bartlett

  • Boosting the margin: a new explanation for the effectiveness of voting methods

    Robert E. Schapire;Yoav Freund;Peter Bartlett;Wee Sun Lee

  • Rademacher and gaussian complexities: risk bounds and structural results

    Peter L. Bartlett;Shahar Mendelson

  • Learning the Kernel Matrix with Semidefinite Programming

    Gert R. G. Lanckriet;Nello Cristianini;Peter Bartlett;Laurent El Ghaoui

  • Neural Network Learning: Theoretical Foundations

    Martin Anthony;Peter L. Bartlett

  • The sample complexity of pattern classification with neural networks: the size of the weights is more important than the size of the network

    P.L. Bartlett

  • Convexity, Classification, and Risk Bounds

    Peter L Bartlett;Michael I Jordan;Jon D McAuliffe

  • Boosting Algorithms as Gradient Descent in Function Space

    Llew Mason;Jonathan Baxter;Peter Bartlett;Marcus Frean

  • Advances in Large Margin Classifiers

    Alexander J. Smola;Peter J. Bartlett

  • Infinite-horizon policy-gradient estimation

    Jonathan Baxter;Peter L. Bartlett

  • Boosting Algorithms as Gradient Descent

    Llew Mason;Jonathan Baxter;Peter L. Bartlett;Marcus R. Frean

  • Local Rademacher complexities

    Peter L. Bartlett;Olivier Bousquet;Shahar Mendelson

  • Probabilities for SV Machines

    Alexander J. Smola;Peter Bartlett;Bernhard Schölkopf;Dale Schuurmans

  • Structural risk minimization over data-dependent hierarchies

    J. Shawe-Taylor;P.L. Bartlett;R.C. Williamson;M. Anthony

  • Spectrally-normalized margin bounds for neural networks

    Peter L. Bartlett;Peter L. Bartlett;Dylan J. Foster;Matus Jan Telgarsky

  • Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates

    Dong Yin;Yudong Chen;Kannan Ramchandran;Peter L. Bartlett

  • RL^2: Fast Reinforcement Learning via Slow Reinforcement Learning

    Yan Duan;John Schulman;Xi Chen;Peter L. Bartlett

  • Benign overfitting in linear regression

    Peter L. Bartlett;Philip M. Long;Gábor Lugosi;Alexander Tsigler

  • Model Selection and Error Estimation

    Peter L. Bartlett;Stéphane Boucheron;Gábor Lugosi

  • Variance Reduction Techniques for Gradient Estimates in Reinforcement Learning

    Evan Greensmith;Peter L. Bartlett;Jonathan Baxter

Frequent Co-Authors

Michael I. Jordan
Michael I. Jordan University of California, Berkeley
Robert C. Williamson
Robert C. Williamson University of Tübingen
Alexander J. Smola
Alexander J. Smola Amazon (United States)
Bernhard Schölkopf
Bernhard Schölkopf Max Planck Institute for Intelligent Systems
Alekh Agarwal
Alekh Agarwal Google (United States)
Dale Schuurmans
Dale Schuurmans University of Alberta
Ambuj Tewari
Ambuj Tewari University of Michigan–Ann Arbor
Wee Sun Lee
Wee Sun Lee National University of Singapore

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 online education offers flexibility for students interested in computer science and related fields. For those just starting, pursuing one of the easy online associate degrees can be a smart first step, allowing you to gain foundational knowledge and quickly enter the workforce.

Budget is a key concern for many students. To minimize expenses while maximizing quality, it's important to look into the cheapest online edd programs. This can be a great path for those seeking advanced leadership roles in technology and education fields.

Choosing the right institution is equally crucial. Many students consider enrolling in the most popular online colleges for wider recognition and better networking opportunities.

If your interests lie at the intersection of technology and creativity, you might pursue a game art degree online, tapping into the fast-growing video game industry.

With so many versatile online options, students can tailor their educational journey to fit their career goals and lifestyles.

Best Scientists Citing Peter L. Bartlett

Trending Scientists