2026 Akshay Krishnamurthy: Computer Science Researcher – H-Index, Publications & Awards

Discipline name	D-Index	World Ranking	Current World Ranking	National Ranking	Current National Ranking	Publications	Citations
Computer Science	36	11401	11077	4685	4485	106	4136

Overview

Akshay Krishnamurthy is affiliated with Microsoft in the United States and has contributed extensively to the field of computer science, with a focus on artificial intelligence and operations research. Their research work spans multiple subfields including artificial intelligence, management science and operations research, computer networks and communications, signal processing, and control and systems engineering.

Their work covers key topics such as advanced bandit algorithms research, machine learning and algorithms, reinforcement learning in robotics, domain adaptation and few-shot learning, machine learning and data classification, data stream mining techniques, and topic modeling.

Notable recent papers authored or co-authored by Akshay Krishnamurthy include:

FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPs (2020), published in arXiv (Cornell University)
Information Theoretic Regret Bounds for Online Nonlinear Control (2020), published in arXiv (Cornell University)
Reward-Free Exploration for Reinforcement Learning (2020), published in arXiv (Cornell University)
Contrastive estimation reveals topic posterior information to linear models (2020), published in arXiv (Cornell University)
Trace Reconstruction: Generalized and Parameterized (2021), published in IEEE Transactions on Information Theory

Frequent co-authors collaborating with Akshay Krishnamurthy include:

Dylan J. Foster
Sham M. Kakade
Cyril Zhang
Jordan T. Ash
Max Simchowitz

The majority of their papers have been published in venues such as arXiv (Cornell University), where 54 publications are recorded. Other publication venues include Operations Research, IEEE Transactions on Information Theory, and the Journal of Dr. YSR University of Health Sciences.

Their research intersects various advanced machine learning areas and operational research disciplines, often focusing on the theoretical aspects of learning algorithms and their applications in control, robotics, and data classification. This reflects a broad range of methodological approaches within computer science and artificial intelligence domains.

Best Publications

Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning.

Rajarshi Das;Shehzaad Dhuliawala;Manzil Zaheer;Luke Vilnis

407
Citations
Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds

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

357
Citations
Contextual decision processes with low Bellman rank are PAC-learnable

Nan Jiang;Akshay Krishnamurthy;Alekh Agarwal;John Langford

216
Citations
Learning to Search Better than Your Teacher

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

182
Citations
Parallelised Bayesian Optimisation via Thompson Sampling

Kirthevasan Kandasamy;Akshay Krishnamurthy;Jeff Schneider;Barnabás Póczos

156
Citations
Low-Rank Matrix and Tensor Completion via Adaptive Sampling

Akshay Krishnamurthy;Aarti Singh

153
Citations
DEGAS: De Novo Discovery of Dysregulated Pathways in Human Diseases

Igor Ulitsky;Akshay Krishnamurthy;Richard M. Karp;Ron Shamir

141
Citations
Off-policy evaluation for slate recommendation

Adith Swaminathan;Akshay Krishnamurthy;Alekh Agarwal;Miroslav Dudík

135
Citations
A Hierarchical Algorithm for Extreme Clustering

Ari Kobren;Nicholas Monath;Akshay Krishnamurthy;Andrew McCallum

112
Citations
Noise Thresholds for Spectral Clustering

Sivaraman Balakrishnan;Min Xu;Akshay Krishnamurthy;Aarti Singh

111
Citations
Nonparametric von Mises estimators for entropies, divergences and mutual informations

Kirthevasan Kandasamy;Akshay Krishnamurthy;Barnabÿs Póczos;Larry Wasserman

108
Citations
Provably efficient RL with Rich Observations via Latent State Decoding

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

104
Citations
Efficient Active Algorithms for Hierarchical Clustering

Akshay Krishnamurthy;Sivaraman Balakrishnan;Min Xu;Aarti Singh

92
Citations
Nonparametric Estimation of Renyi Divergence and Friends

Akshay Krishnamurthy;Kirthevasan Kandasamy;Barnabas Poczos;Larry Wasserman

83
Citations
Model-based RL in Contextual Decision Processes: PAC bounds and Exponential Improvements over Model-free Approaches

Wen Sun;Nan Jiang;Akshay Krishnamurthy;Alekh Agarwal

82
Citations
PAC reinforcement learning with rich observations

Akshay Krishnamurthy;Alekh Agarwal;John Langford

79
Citations
Optimism in Reinforcement Learning with Generalized Linear Function Approximation

Yining Wang;Ruosong Wang;Simon Shaolei Du;Akshay Krishnamurthy

76
Citations
Efficient algorithms for adversarial contextual learning

Vasilis Syrgkanis;Akshay Krishnamurthy;Robert E. Schapire

69
Citations
Transformers Learn Shortcuts to Automata

Unknown

68
Citations
Reward-Free Exploration for Reinforcement Learning

Chi Jin;Akshay Krishnamurthy;Max Simchowitz;Tiancheng Yu

59
Citations
Kinematic State Abstraction and Provably Efficient Rich-Observation Reinforcement Learning

Dipendra Misra;Mikael Henaff;Akshay Krishnamurthy;John Langford

51
Citations
On oracle-efficient PAC RL with rich observations

Christoph Dann;Nan Jiang;Akshay Krishnamurthy;Alekh Agarwal

32
Citations

Frequent Co-Authors

John Langford Microsoft (United States)

Alekh Agarwal Google (United States)

Aarti Singh Carnegie Mellon University

Robert E. Schapire Microsoft (United States)

Miroslav Dudík Microsoft (United States)

Barnabás Póczos Carnegie Mellon University

Sham M. Kakade Harvard University

Larry Wasserman Carnegie Mellon University

Andrew McCallum University of Massachusetts Amherst

Andrew McGregor University of Massachusetts Amherst

External Links

Personal website of Akshay Krishnamurthy

If you think any of the details on this page are incorrect, let us know.

Related Online Degrees & Career Pathways

As technology advances, more students explore flexible learning options. Pursuing an online computer science degree can jumpstart your tech career without pausing work or family commitments. These programs offer a robust curriculum in coding, algorithms, and software design, preparing you for fast-growing tech jobs.

Interested in applying computer science principles to real-world problems? Online options abound in complementary fields. For example, an online environmental engineering degree combines technology and sustainability, while the cheapest online mechanical engineering degree programs provide affordable pathways into design, manufacturing, and robotics.

For those fascinated by the laws of nature or aiming for careers in research, teaching, or tech innovation, you may wonder, can you get a physics degree online? Today, flexible online physics programs can help you build a strong analytical background from anywhere in the world.

Exploring these related online degrees opens up a wealth of career possibilities across science, engineering, and technology fields—often with the added benefits of flexible schedules and significant cost savings.