I am a postdoc at the University of Pennsylvania, hosted by Nikolai Matni and George J. Pappas and generously funded by a Swedish Research Council Grant. Previously, I obtained a PhD under the supervision of Henrik Sandberg at KTH. You can find an interview with me about my PhD Work here.
Research Interests
- Machine Learning Theory, Controls, Statistics
Papers
For a full list, please refer to my Google Scholar.
Selected Papers
Sharp Rates in Dependent Learning Theory: Avoiding Sample Size Deflation for the Square Loss, Ingvar Ziemann, Stephen Tu, George J. Pappas and Nikolai Matni, ICML24. Spotlight.
The Noise Level in Dependent Linear Regression, Ingvar Ziemann, Stephen Tu, George J. Pappas and Nikolai Matni, NeurIPS’23.
Learning with little mixing, Ingvar Ziemann and Stephen Tu, NeurIPS’22.
How are policy gradient methods affected by the limits of control?, Ingvar Ziemann, Anastasios Tsiamis, Henrik Sandberg and Nikolai Matni, IEEE CDC’22. Best Student Paper Award.
Regret Lower Bounds for Learning Linear Quadratic Gaussian Systems, Ingvar Ziemann and Henrik Sandberg, to appear, IEEE Transactions on Automatic Control.
Statistical Learning Theory for Control, Anastasios Tsiamis, Ingvar Ziemann, Nikolai Matni and George J. Pappas, IEEE Control Systems Magazine 2023.