Zhang Junyu

Zhang Junyu is an Assistant Professor in the Department of Industrial Systems Engineering and Management at the National University of Singapore (NUS). He is affiliated with the Institute of Operations Research and Analytics (IORA), part of NUS’s Smart Nation Research Cluster. His research focuses on optimization algorithms, reinforcement learning, and machine learning, with particular expertise in stochastic optimization, decentralized systems, and convex/non-convex analysis.

Key research areas include first-order methods for saddle point problems, variance reduction techniques in stochastic optimization, and policy search in continuous control. His work bridges theoretical foundations (e.g., complexity bounds, convergence guarantees) with practical applications in reinforcement learning and distributed systems.

Zhang has contributed extensively to publications on primal-dual algorithms, temporal difference learning with deep neural networks, and multi-agent reinforcement learning frameworks. His research emphasizes algorithmic efficiency and robustness, with applications in areas like decentralized actor-critic methods and off-policy learning in constrained Markov decision processes.

No scientific awards or grants are explicitly mentioned in the provided text. His academic contributions are centered around advancing optimization theory and its intersections with machine learning, particularly in high-dimensional and non-convex problem domains.