2026-09-20T20:29:36Z https://www.ideals.illinois.edu/oai-pmh

oai:www.ideals.illinois.edu:2142/129869 2025-10-25 col_2142_5131 col_2142_14787 com_2142_5130 com_2142_9630 com_2142_234

application/pdf en text Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-20 without embargo terms The student, Negin Musavi, accepted the attached license on 2025-07-11 at 15:04. The student, Negin Musavi, submitted this Dissertation for approval on 2025-07-11 at 17:42. This Dissertation was approved for publication on 2025-07-16 at 10:31. DSpace SAF Submission Ingestion Package generated from Vireo submission #22523 on 2025-10-20 at 16:57:52 Learning in dynamical systems with guarantees: from system identification to safety verification and fast adaptation Musavi, Negin 2025-07-16 Dullerud, Geir E. Dullerud, Geir Li, Yingying Mitra, Sayan Srikant, Rayadurgam West, Matthew System Identification Safety Verification Meta Learning eng This thesis investigates the sample complexity of data-driven algorithms for learning in controlled dynamical systems. As more systems operate in environments where models are unknown but data are available, understanding how efficiently learning algorithms use data becomes increasingly important. The thesis addresses three central problems in this context. First, it establishes conditions under which unknown parameters in nonlinear systems can be efficiently learned via non-active exploration, showing that linearly parameterized systems with real-analytic features can be identified using least-squares and set-membership estimators. Second, it develops a framework for verifying safety and synthesizing parameters in unknown systems with hybrid state spaces, leveraging a new bandit-based method—Hybrid Hierarchical Optimistic Optimization (HyHOO)—that extends prior work in black-box optimization. Finally, the thesis explores meta-learning for optimal control, proposing methods to exploit shared structure across related control tasks for fast adaptation in new control tasks. The results contribute theoretical guarantees, practical algorithms, and experimental validations toward a deeper understanding of data efficiency in learning dynamical systems. 2025-08 Text https://hdl.handle.net/2142/129869 Copyright 2025 Negin Musavi Mechanical Sci & Engineering Mechanical Engineering University of Illinois Urbana-Champaign Ph.D. Dissertation