Orest Xherija

University of Chicago

Papers

1

Total Citations

10

H-Index

1

About

Orest Xherija’s research lies at the intersection of machine learning, control theory, and dynamical systems, with a focus on developing algorithms that are both theoretically grounded and practically efficient. His most-cited work, “Memory-Efficient Learning of Stable Linear Dynamical Systems for Prediction and Control” (2020, 10 citations), introduces a novel algorithm that learns stable linear dynamical systems (LDS) from data by simultaneously minimizing reconstruction error and enforcing stability. By leveraging a recent characterization of stable matrices, Xherija’s approach overcomes key computational bottlenecks, enabling memory-efficient learning without sacrificing predictive accuracy. This contribution is particularly impactful for applications in robotics, time-series forecasting, and control, where stability guarantees are critical. Xherija’s work demonstrates a rare ability to bridge rigorous mathematical theory with real-world algorithmic design, making his research highly relevant for students and practitioners seeking scalable, stable models. His focus on memory efficiency addresses a growing need in resource-constrained environments, positioning him as a promising voice in the next generation of systems and control researchers.

Research Focus

Key Achievements

1
H-Index
1
Papers
10
Total Citations
10
Avg Citations/Paper
🏆 Most Cited Paper
Memory-Efficient Learning of Stable Linear Dynamical Systems for Prediction and Control
10 citations · 2020
📈 Most Prolific Year: 2020 (1 Papers)
🤝 Key Collaborators: 2
🏛 Institutions: University of Chicago

Top Papers

  1. 1

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 12 days ago