World's Best Scientists 2026 revealed!

D-Index & Metrics

Computer Science

D-Index
53
Citations
11027
World Ranking
4834
National Ranking
2250

Overview

Alekh Agarwal is affiliated with Google in the United States and has contributed extensively to the fields of Computer Science and Decision Sciences. Their work spans several subfields, including Artificial Intelligence, Management Science and Operations Research, Information Systems, Statistical and Nonlinear Physics, and Control and Systems Engineering.

Their research topics primarily focus on advanced techniques and methodologies in machine learning and artificial intelligence. Key areas include:

  • Advanced Bandit Algorithms Research
  • Reinforcement Learning in Robotics
  • Adversarial Robustness in Machine Learning
  • Model Reduction and Neural Networks
  • Machine Learning and Algorithms
  • Stochastic Gradient Optimization Techniques
  • Evolutionary Algorithms and Applications

Alekh Agarwal has been involved in numerous publications, with a strong presence in venues such as arXiv (Cornell University), Proceedings of the AAAI Conference on Artificial Intelligence, and PLoS ONE. There are 45 publications in arXiv alone, indicating a significant engagement with open-access preprint dissemination.

Recent papers authored or co-authored by Alekh Agarwal include:

  • Safe Reinforcement Learning via Curriculum Induction, 2020, arXiv (Cornell University)
  • FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPs, 2020, arXiv (Cornell University)
  • Provably Good Batch Reinforcement Learning Without Great Exploration, 2020, arXiv (Cornell University)
  • PC-PG: Policy Cover Directed Exploration for Provable Policy Gradient Learning, 2020, arXiv (Cornell University)
  • Federated Residual Learning, 2020, arXiv (Cornell University)

Collaboration is a significant component of their work. Frequent co-authors include Ching-An Cheng, Tong Zhang, Akshay Krishnamurthy, Christoph Dann, and Jacob Eisenstein. These collaborations highlight connections across researchers specializing in machine learning and related disciplines.

Best Publications

  • Dual Averaging for Distributed Optimization: Convergence Analysis and Network Scaling

    J. C. Duchi;A. Agarwal;M. J. Wainwright

  • Distributed delayed stochastic optimization

    Alekh Agarwal;John C. Duchi

  • Noisy matrix decomposition via convex relaxation: Optimal rates in high dimensions

    Alekh Agarwal;Sahand N. Negahban;Martin J. Wainwright

  • A Reductions Approach to Fair Classification

    Alekh Agarwal;Alina Beygelzimer;Miroslav Dudík;John Langford

  • A reliable effective terascale linear learning system

    Alekh Agarwal;Olivier Chapelle;Miroslav Dudík;John Langford

  • Taming the Monster: A Fast and Simple Algorithm for Contextual Bandits

    Alekh Agarwal;Daniel Hsu;Satyen Kale;John Langford

  • Information-theoretic lower bounds on the oracle complexity of convex optimization

    Alekh Agarwal;Peter L. Bartlett;Pradeep Ravikumar;Martin J. Wainwright

  • Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds

    Jordan T. Ash;Chicheng Zhang;Akshay Krishnamurthy;John Langford

  • Optimal Algorithms for Online Convex Optimization with Multi-Point Bandit Feedback.

    Alekh Agarwal;Ofer Dekel;Lin Xiao

  • Fast global convergence of gradient methods for high-dimensional statistical recovery

    Alekh Agarwal;Sahand N. Negahban;Martin J. Wainwright

  • Information-Theoretic Lower Bounds on the Oracle Complexity of Stochastic Convex Optimization

    A. Agarwal;P. L. Bartlett;P. Ravikumar;M. J. Wainwright

  • Optimality and Approximation with Policy Gradient Methods in Markov Decision Processes

    Alekh Agarwal;Sham M. Kakade;Jason D. Lee;Gaurav Mahajan

  • Contextual decision processes with low Bellman rank are PAC-learnable

    Nan Jiang;Akshay Krishnamurthy;Alekh Agarwal;John Langford

  • On the Theory of Policy Gradient Methods: Optimality, Approximation, and Distribution Shift

    Alekh Agarwal;Sham M. Kakade;Jason D. Lee;Gaurav Mahajan

  • Learning to Search Better than Your Teacher

    Kai-Wei Chang;Akshay Krishnamurthy;Alekh Agarwal;Hal Daume

  • Stochastic Convex Optimization with Bandit Feedback

    Alekh Agarwal;Dean P. Foster;Daniel J. Hsu;Sham M. Kakade

  • Learning Sparsely Used Overcomplete Dictionaries via Alternating Minimization

    Alekh Agarwal;Animashree Anandkumar;Prateek Jain;Praneeth Netrapalli

  • Fast global convergence rates of gradient methods for high-dimensional statistical recovery

    Alekh Agarwal;Sahand Negahban;Martin J Wainwright

  • Information-theoretic lower bounds on the oracle complexity of convex optimization

    Alekh Agarwal;Martin J Wainwright;Peter L. Bartlett;Pradeep K. Ravikumar

  • Learning to rank networked entities

    Alekh Agarwal;Soumen Chakrabarti;Sunny Aggarwal

  • Fast convergence of regularized learning in games

    Vasilis Syrgkanis;Alekh Agarwal;Haipeng Luo;Robert E. Schapire

  • Provably efficient RL with Rich Observations via Latent State Decoding

    Simon S. Du;Akshay Krishnamurthy;Nan Jiang;Alekh Agarwal

  • Model-based RL in Contextual Decision Processes: PAC bounds and Exponential Improvements over Model-free Approaches

    Wen Sun;Nan Jiang;Akshay Krishnamurthy;Alekh Agarwal

Frequent Co-Authors

John Langford
John Langford Microsoft (United States)
Akshay Krishnamurthy
Akshay Krishnamurthy Microsoft (United States)
Miroslav Dudík
Miroslav Dudík Microsoft (United States)
Robert E. Schapire
Robert E. Schapire Microsoft (United States)
Peter L. Bartlett
Peter L. Bartlett University of California, Berkeley
John C. Duchi
John C. Duchi Stanford University
Sham M. Kakade
Sham M. Kakade Harvard University
Hal Daumé
Hal Daumé University of Maryland, College Park
Daniel Hsu
Daniel Hsu Columbia 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 different pathways in computer science can open up a world of opportunities, even if you have a non-traditional academic background. For students interested in advancing their skills, some of the most valuable masters degrees in the field, such as Artificial Intelligence and Data Science, are now available fully online. These programs help you remain competitive within a rapidly evolving tech landscape.

If you're seeking quicker entry into the industry, many reputable colleges now offer 1 year associate degree programs online. These programs are designed to fast-track your introduction to foundational computer science topics and IT careers, making them ideal for career changers or recent high school graduates.

Affordability is another important factor to consider. Students on a budget can find the cheapest online college options to help reduce costs without sacrificing quality.

Lastly, if your GPA isn't stellar, don't let that hold you back. Several of the universities for low gpa still offer flexible and reputable computer science programs online, ensuring you have access to quality education and career prospects regardless of your academic history.

Best Scientists Citing Alekh Agarwal

Trending Scientists