World's Best Scientists 2026 revealed!

D-Index & Metrics

Computer Science

D-Index
32
Citations
8641
World Ranking
12888
National Ranking
5199

Overview

Alex Olshevsky is affiliated with Boston University in the United States and specializes in the field of Computer Science. Their research primarily focuses on subfields such as Artificial Intelligence, Computer Networks and Communications, Computational Mechanics, Statistical and Nonlinear Physics, and Public Health, Environmental and Occupational Health.

The scientist's work encompasses several main topics including Stochastic Gradient Optimization Techniques, Distributed Control Multi-Agent Systems, Sparse and Compressive Sensing Techniques, Reinforcement Learning in Robotics, Model Reduction and Neural Networks, Mathematical and Theoretical Epidemiology and Ecology Models, as well as COVID-19 epidemiological studies.

Alex Olshevsky has contributed numerous publications to a range of venues. Frequent publication outlets include:

  • arXiv (Cornell University)
  • IEEE Control Systems Letters
  • IEEE Transactions on Automatic Control
  • IEEE Signal Processing Magazine
  • SIAM Journal on Control and Optimization

The scientist's recent papers demonstrate a focus on distributed and stochastic optimization as well as control and matrix completion techniques. Selected recent publications include:

  • "Asymptotic Network Independence in Distributed Stochastic Optimization for Machine Learning: Examining Distributed and Centralized Stochastic Gradient Descent," 2020, IEEE Signal Processing Magazine
  • "A Sharp Estimate on the Transient Time of Distributed Stochastic Gradient Descent," 2021, IEEE Transactions on Automatic Control
  • "Adversarial Crowdsourcing Through Robust Rank-One Matrix Completion," 2020, arXiv (Cornell University)
  • "Deterministic and Randomized Actuator Scheduling With Guaranteed Performance Bounds," 2020, IEEE Transactions on Automatic Control
  • "Local SGD With a Communication Overhead Depending Only on the Number of Workers," 2020, arXiv (Cornell University)

Collaborations have been a notable aspect of their scientific activity. Frequent co-authors include:

  • Ioannis Ch. Paschalidis
  • Arsenii Mustafin
  • Bahman Gharesifard
  • Haoxing Tian
  • Shi Pu

Best Publications

  • Distributed optimization over time-varying directed graphs

    Angelia Nedic;Alex Olshevsky

  • Convergence in Multiagent Coordination, Consensus, and Flocking

    V.D. Blondel;J.M. Hendrickx;A. Olshevsky;J.N. Tsitsiklis

  • Achieving Geometric Convergence for Distributed Optimization Over Time-Varying Graphs

    Angelia Nedić;Alex Olshevsky;Wei Shi

  • Convergence Speed in Distributed Consensus and Averaging

    Alex Olshevsky;John N. Tsitsiklis

  • Federated learning of predictive models from federated Electronic Health Records.

    Theodora S. Brisimi;Ruidi Chen;Theofanie Mela;Alex Olshevsky

  • On distributed averaging algorithms and quantization effects

    A. Nedic;A. Olshevsky;A. Ozdaglar;J.N. Tsitsiklis

  • Network Topology and Communication-Computation Tradeoffs in Decentralized Optimization

    Angelia Nedic;Alex Olshevsky;Michael G. Rabbat

  • Minimal Controllability Problems

    Alexander Olshevsky

  • Stochastic Gradient-Push for Strongly Convex Functions on Time-Varying Directed Graphs

    Angelia Nedic;Alex Olshevsky

  • Convergence Rates in Distributed Consensus and Averaging

    A. Olshevsky;J.N. Tsitsiklis

  • Distributed subgradient methods and quantization effects

    A. Nedic;A. Olshevsky;A. Ozdaglar;J.N. Tsitsiklis

  • Fast Convergence Rates for Distributed Non-Bayesian Learning

    Angelia Nedic;Alex Olshevsky;Cesar A. Uribe

  • Network Lifetime and Power Assignment in ad hoc Wireless Networks

    Gruia Calinescu;Sanjiv Kapoor;Alexander Olshevsky;Alexander Zelikovsky

  • NP-hardness of deciding convexity of quartic polynomials and related problems

    Amir Ali Ahmadi;Alexander Olshevsky;Pablo A. Parrilo;John N. Tsitsiklis

  • Geometrically convergent distributed optimization with uncoordinated step-sizes

    Angelia Nedic;Alex Olshevsky;Wei Shi;Cesar A. Uribe

  • Matrix $p$-Norms Are NP-Hard to Approximate If $p eq1,2,\infty$

    Julien M. Hendrickx;Alex Olshevsky

  • Nonasymptotic convergence rates for cooperative learning over time-varying directed graphs

    Angelia Nedic;Alex Olshevsky;Cesar A. Uribe

  • Linear Time Average Consensus on Fixed Graphs and Implications for Decentralized Optimization and Multi-Agent Control

    Alex Olshevsky

  • On the Nonexistence of Quadratic Lyapunov Functions for Consensus Algorithms

    A. Olshevsky;J.N. Tsitsiklis

  • Improved Convergence Rates for Distributed Resource Allocation

    Angelia Nedic;Alex Olshevsky;Wei Shi

  • Minimum input selection for structural controllability

    Alex Olshevsky

  • A Sharp Estimate on the Transient Time of Distributed Stochastic Gradient Descent

    Shi Pu;Alexander Olshevsky;Ioannis Ch. Paschalidis

  • Linear Time Average Consensus and Distributed Optimization on Fixed Graphs

    Alex Olshevsky

  • Distributed Anonymous Discrete Function Computation

    J. M. Hendrickx;A. Olshevsky;J. N. Tsitsiklis

  • Achieving Geometric Convergence for Distributed Optimization over Time-Varying Graphs

    Angelia Nedich;Alex Olshevsky;Wei Shi

  • Distributed optimization over time-varying directed graphs

    Angelia Nedic;Alex Olshevsky

Frequent Co-Authors

Angelia Nedic
Angelia Nedic Arizona State University
Julien M. Hendrickx
Julien M. Hendrickx Université Catholique de Louvain
Ioannis Ch. Paschalidis
Ioannis Ch. Paschalidis Boston University
Venkatesh Saligrama
Venkatesh Saligrama Boston University
Vincent D. Blondel
Vincent D. Blondel Université Catholique de Louvain
Alexander Zelikovsky
Alexander Zelikovsky Georgia State University
Csaba Szepesvári
Csaba Szepesvári University of Alberta
Tamer Basar
Tamer Basar University of Illinois at Urbana-Champaign

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 studies in the USA opens up a wide range of online degree and career options. Many students worry about admissions requirements—fortunately, some online graduate schools with low gpa requirements provide flexible pathways to earn a degree, even if your academic background isn’t perfect.

If you’re interested in entering the tech industry quickly, enrolling in a computer science accelerated program is a viable option. These programs allow you to complete your degree on a faster timeline, often without sacrificing educational quality or career preparedness.

Computer science expertise can also support diverse and emerging job roles. For example, with an interdisciplinary focus, you’ll find that the question of what jobs can you get with an environmental science degree now includes tech-driven roles such as data analyst, GIS specialist, or environmental software developer.

If you’re looking for a cost-effective way to blend technology and sustainability, consider the most affordable online environmental engineering degree programs. These programs offer technical skills that are increasingly in demand, helping you build a future-ready career.

Best Scientists Citing Alex Olshevsky

Trending Scientists

Recently Published Articles