Dariush Fooladivanda
Papers
2
Total Citations
9
H-Index
2
About
Dariush Fooladivanda is a researcher whose work sits at the intersection of machine learning, control theory, and dynamical systems. His research focuses on developing rigorous algorithms for learning and decision-making in uncertain, complex environments — a challenge central to modern robotics, autonomous systems, and cyber-physical infrastructure. Fooladivanda's most notable contribution is a novel online learning algorithm designed for unknown and uncertain dynamical environments that are fully observable. A key innovation of this work is its probabilistic characterization of systems subject to additive subGaussian disturbances, providing finite-sample guarantees — a theoretically rigorous assurance of algorithm performance with limited data. This addresses a critical gap in real-world deployment of learning-based systems, where data is often scarce and uncertainty is unavoidable. The work has garnered citations across both its 2020 and 2021 publications, reflecting sustained interest from the research community working on safe and reliable autonomous systems. His contributions are particularly valuable for researchers tackling parameterized uncertain environments, where classical control approaches fall short. By bridging statistical learning theory with dynamical systems, Fooladivanda's work offers principled tools for building adaptive, safety-aware systems — making his research highly relevant to students and practitioners in control engineering, reinforcement learning, and robotics.
Research Focus
Key Achievements
Top Papers
- 1
- 2