PhD Thesis Defense

This thesis advances fine-grained reasoning under limited human supervision through several complementary approaches.

This dissertation addresses potential failure points in artificial agents.

This dissertation examines techniques for learning structure and discusses how the resulting background knowledge is used in decision making under uncertainty.

This dissertation studies algorithmic methods for constructing and optimizing threshold-logic circuits.

This dissertation explores how low-overhead dynamic analysis can be used to improve the reliability of Python software.

This dissertation makes generative retrieval scalable and practical.

This dissertation develops a comprehensive framework for high-fidelity motion characterization, addressing challenges of sensitivity, robustness, and privacy.

Health care unfolds through linked decisions rather than isolated responses. We study two research programs.

This dissertation advances the design of practical privacy-preserving machine learning systems.

This dissertation develops resource-efficient decision-making algorithms to optimize the performance of networked systems under such constraints.

This thesis develops control frameworks for legged robots that bridge model-based trajectory optimization and data-driven learning

The central argument of this thesis is that effective search in such regimes requires evolving belief.