← Authors

Alex Olshevsky

11 papers · 2020–2025 · 5 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird 🌍 Conference Polyglot (5) πŸƒ Academic Marathon (5) 🐝 Cross-Pollinator (8) 🌈 Renaissance Researcher (5) πŸŒ‰ Interdisciplinary Bridge πŸ—ΊοΈ Taxonomy Completionist (20) 🧭 Keyword Pioneer πŸ’Ž Century Club (11)

Conferences

JMLR (4) NIPS (3) ICML (2) AISTATS (1) ICLR (1)

Top co-authors

Ioannis Paschalidis (2) Venkatesh Saligrama (2) Yannis Paschalidis (2) Artin Spiridonoff (2) Haoxing Tian (2) Amirreza Neshaei Moghaddam (1) Bahman Gharesifard (1) Ioannis Ch. Paschalidis (1) Rui Liu (1) Csaba SzepesvΓ‘ri (1)

Research topics

Statistics (1)

Keywords

distributed optimization (3) matrix completion (2) rank-one matrix (2) gradient descent (2) convergence analysis (1) sample complexity (1) temporal difference learning (1) markov decision process (1) parameter estimation (1) discount factor (1) parallel optimization (1) value function approximation (1) communication efficiency (1) alternating minimization (1) linear quadratic regulator (1) distributed learning (1) adversarial robustness (1) bradley-terry-luce model (1) pairwise comparison (1) stochastic gradient descent (1)

Papers

Sample Complexity of the Linear Quadratic Regulator: A Reinforcement Learning Lens JMLR 2025
MDP Geometry, Normalization and Reward Balancing Solvers AISTATS 2025
Convergence of Actor-Critic with Multi-Layer Neural Networks NIPS 2023
On the Performance of Temporal Difference Learning With Neural Networks ICLR 2023
Asymptotic Network Independence and Step-Size for a Distributed Subgradient Method JMLR 2022
Communication-efficient SGD: From Local SGD to One-Shot Averaging NIPS 2021
Temporal Difference Learning as Gradient Splitting ICML 2021
Minimax Rate for Learning From Pairwise Comparisons in the BTL Model ICML 2020
Adversarial Crowdsourcing Through Robust Rank-One Matrix Completion NIPS 2020
Robust Asynchronous Stochastic Gradient-Push: Asymptotically Optimal and Network-Independent Performance for Strongly Convex Functions JMLR 2020
Gradient Descent for Sparse Rank-One Matrix Completion for Crowd-Sourced Aggregation of Sparsely Interacting Workers JMLR 2020