World's Best Scientists 2026 revealed!
Ankur Moitra

Ankur Moitra

D-Index & Metrics

Computer Science

D-Index
43
Citations
6484
World Ranking
8081
National Ranking
3465

Mathematics

D-Index
43
Citations
6413
World Ranking
1719
National Ranking
739

Overview

Ankur Moitra is a researcher affiliated with MIT in the United States, specializing in computer science and mathematics. Their work spans multiple subfields, including artificial intelligence, statistics and probability, statistical and nonlinear physics, computational theory and mathematics, and computational mechanics.

Their research topics cover areas such as machine learning and algorithms, Bayesian modeling and causal inference, sparse and compressive sensing techniques, Markov chains and Monte Carlo methods, statistical methods and inference, tensor decomposition and applications, and reinforcement learning in robotics.

Recent papers authored or co-authored by Ankur Moitra include:

  • Noisy tensor completion via the sum-of-squares hierarchy, 2022, Mathematical Programming
  • Distilling Model Failures as Directions in Latent Space, 2022, arXiv (Cornell University)
  • Classification Under Misspecification: Halfspaces, Generalized Linear Models, and Connections to Evolvability, 2020, arXiv (Cornell University)
  • Rigorous Guarantees for Tyler's M-estimator via quantum expansion, 2020, arXiv (Cornell University)
  • Algorithmic Foundations for the Diffraction Limit, 2020, arXiv (Cornell University)

Frequent co-authors collaborating with Moitra include Allen Liu, Noah Golowich, Dhruv Rohatgi, Ainesh Bakshi, and Alexander S. Wein.

Frequently chosen venues for publication encompass:

  • arXiv (Cornell University)
  • Mathematical Programming
  • Israel Journal of Mathematics
  • Communications of the ACM
  • 2022 IEEE 63rd Annual Symposium on Foundations of Computer Science (FOCS)

Ankur Moitra has contributed substantially to the scientific literature with 74 publications in computer science and 31 in mathematics. Within these disciplines, the focus on artificial intelligence through 54 works and 19 on statistics and probability highlights the interdisciplinary nature of their research.

Best Publications

  • Learning Topic Models -- Going beyond SVD

    Sanjeev Arora;Rong Ge;Ankur Moitra

  • A Practical Algorithm for Topic Modeling with Provable Guarantees

    Sanjeev Arora;Rong Ge;Yonatan Halpern;David Mimno

  • Computing a nonnegative matrix factorization -- provably

    Sanjeev Arora;Rong Ge;Ravindran Kannan;Ankur Moitra

  • Settling the Polynomial Learnability of Mixtures of Gaussians

    Ankur Moitra;Gregory Valiant

  • Efficiently learning mixtures of two Gaussians

    Adam Tauman Kalai;Ankur Moitra;Gregory Valiant

  • New Algorithms for Learning Incoherent and Overcomplete Dictionaries

    Sanjeev Arora;Rong Ge;Ankur Moitra

  • Robust Estimators in High-Dimensions Without the Computational Intractability

    Ilias Diakonikolas;Gautam Kamath;Daniel Kane;Jerry Li

  • Robust Estimators in High Dimensions without the Computational Intractability

    Ilias Diakonikolas;Gautam Kamath;Daniel M. Kane;Jerry Li

  • Simple, Efficient, and Neural Algorithms for Sparse Coding

    Sanjeev Arora;Rong Ge;Tengyu Ma;Ankur Moitra

  • Being Robust (in High Dimensions) Can Be Practical

    Ilias Diakonikolas;Gautam Kamath;Daniel M. Kane;Jerry Li

  • Optimality and Sub-optimality of PCA I: Spiked Random Matrix Models

    Amelia Perry;Alexander S. Wein;Afonso S. Bandeira;Ankur Moitra

  • Super-resolution, Extremal Functions and the Condition Number of Vandermonde Matrices

    Ankur Moitra

  • Noisy Tensor Completion via the Sum-of-Squares Hierarchy

    Boaz Barak;Ankur Moitra

  • Some Results on Greedy Embeddings in Metric Spaces

    Tom Leighton;Ankur Moitra

  • A nearly tight sum-of-squares lower bound for the planted clique problem

    Boaz Barak;Samuel B. Hopkins;Jonathan A. Kelner;Pravesh K. Kothari

  • Smoothed analysis of tensor decompositions

    Aditya Bhaskara;Moses Charikar;Ankur Moitra;Aravindan Vijayaraghavan

  • Approximation Algorithms for Multicommodity-Type Problems with Guarantees Independent of the Graph Size

    Ankur Moitra

  • Robustly learning a gaussian: getting optimal error, efficiently

    Ilias Diakonikolas;Gautam Kamath;Daniel M. Kane;Jerry Li

  • Algorithms and Hardness for Robust Subspace Recovery

    Moritz Hardt;Ankur Moitra

  • Some Results on Greedy Embeddings in Metric Spaces

    A. Moitra;T. Leighton

  • Nonnegative Matrix Factorization

    Ankur Moitra

  • Robustly Learning a Gaussian: Getting Optimal Error, Efficiently

    Alistair Stewart;Ilias Diakonikolas;Gautam Chetan Kamath;Daniel M Kane

Frequent Co-Authors

Rong Ge
Rong Ge Duke University
Sanjeev Arora
Sanjeev Arora Princeton University
Ilias Diakonikolas
Ilias Diakonikolas University of Wisconsin–Madison
Boaz Barak
Boaz Barak Harvard University
Daniel M. Kane
Daniel M. Kane University of California, San Diego
Moses Charikar
Moses Charikar Stanford University
Adam Tauman Kalai
Adam Tauman Kalai Microsoft (United States)
Ryan O'Donnell
Ryan O'Donnell Carnegie Mellon University
Gregory Valiant
Gregory Valiant Stanford 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

For students pursuing Mathematics in the USA, exploring related online degrees can open up diverse career opportunities. For example, a masters degree in marketing blends quantitative skills with business insights, preparing graduates for roles in market analysis and strategy.

If you're interested in leadership roles, many professionals complement their math background with business knowledge through 1 year mba programs in usa. These programs offer accelerated pathways to advance careers without a lengthy time commitment.

Transfer flexibility is also important. Several mba programs that accept transfer credits make it easier for students to leverage previous coursework, smoothing the transition into graduate studies.

Additionally, the rise of big data has increased demand for professionals with strong analytical skills. Pursuing a data analytics master's degree can complement a mathematics degree effectively, leading to careers in data science, business intelligence, and more.

Best Scientists Citing Ankur Moitra

Trending Scientists