Zoom: https://illinois.zoom.us/j/86751720390?pwd=Ub2ppLorYQS7TfUyHAUOfzNn9AAayF.1
Abstract:
Symbolic languages are fundamental to computing: they help us understand and orchestrate unfamiliar concepts and computations in complex domains. Symbolic learning aims to automatically discover concepts expressed in these languages, e.g., formulas or programs, given a few examples, with many applications in programming, testing, and verification of computer systems. Effective algorithms for symbolic learning rely on domain-specific heuristics, which makes them hard to build and limits application in new domains. In the first part of my talk, I will discuss my work on foundations of symbolic learning, which connects language semantics to uniform learning algorithms via an algorithmic meta-theorem. By writing specialized language interpreters, we are able to effectively describe learning algorithms and simultaneously prove new theorems about the decidability of learning in several well-studied symbolic languages in computer science. With this connection, I will explain how a fundamental technique based on version space algebra, as realized in program synthesizers from industry, e.g., Microsoft Excel’s FlashFill, is in fact an instance of a deeper concept related to tree automata. I will discuss how this connection between interpreters and algorithms uncovers a path to efficient specification and design of symbolic learning algorithms for new domains. I will also discuss my work on learning logical formulas and applications to visual discrimination and automated discovery of axiomatizations. In the second part of my talk, I will discuss my work on synthesizing domain-specific languages (DSLs) for few-shot learning, which explores the problem of automatically constructing DSLs that precisely capture a computational domain, balancing expressive power, succinctness, and tractability for effective synthesis in new domains. I will discuss how symbolic concept learning and DSL synthesis together can enable automation of language design beyond applications in synthesis, e.g., for applications in hardware security. Finally, I will conclude with plans for collaborations in machine learning, with a focus on integrating symbolic world knowledge and constraints into learned models as well as the design of general-purpose synthesis algorithms with formal guarantees that scale by leveraging the capabilities of large language models.
Bio:
Paul Krogmeier is a PhD candidate at the University of Illinois Urbana-Champaign. Paul’s research is focused on algorithms for symbolic learning and the problem of learning symbolic languages and abstractions that capture specific domains. His work on symbolic learning was recognized with distinguished paper awards at POPL 2022 and OOPSLA 2023. He has also published in the areas of program synthesis, program verification, and differential privacy.