- Distributed optimization, especially in machine learning.
- Learning from network data
- Multi-agent coordination and control
- Control of networks
For more details, please see my publications by subject area below.
- Adversarial Crowdsourcing Through Robust Rank-One Matrix Completion, Q. Ma, A. Olshevsky, Proceedings of NeurIPS 2020.
- Asymptotic Network Independence in Distributed Optimization for Machine Learning, S. Pu, A. Olshevsky, Y. Paschalidis, IEEE Signal Processing Magazine, 2020.
- Robust Asynchronous Stochastic Gradient Push: Asymptotically Optimal and Network Independent Performance for Strongly Convex Functions, A. Spiridonoff, A. Olshevsky, Y. Paschalidis, Journal of Machine Learning Research, 2020.
- Minimax Rank-1 Matrix Factorization, J. Hendrickx, A. Olshevsky, V. Saligrama, Proceedings of AISTATS 2020.
- Minimax Rate for Pairwise Comparisons in the BTL Model, J. Hendrickx, A. Olshevsky, V. Saligrama, Proceedings of ICML 2020.
- Gradient Descent for Sparse Rank-One Matrix Completion for Crowd-Sourced Aggregation of Sparsely Interacting Workers, Y. Ma, A. Olshevsky, V. Saligrama, C. Szepesvari, Journal of Machine Learning Research, 2020.
- Graph Resistance and Learning from Pairwise Comparisons, J. Hendrickx, A. Olshevsky, V. Saligrama, Proceedings of ICML 2019.
- Network Topology and Communication-Computation Tradeoffs in Distributed Optimization, A. Nedic, A. Olshevsky, M. Rabbat, Proceedings of the IEEE, 2018.
In Spring 2021, I am teaching EC 700, Introduction to Reinforcement Learning.
Email: alexols [at] bu [dot] edu
Office: 531 Photonics Center; 8 St. Mary St, Boston, MA, 02215.