10 citations · 32 across the 7 of their papers we have counts for
7 papers
Synthesizing DSLs for Few-Shot Learning
Paul Krogmeier, P. Madhusudan
We study the problem of synthesizing domain-specific languages (DSLs) for few-shot learning in symbolic domains. Given a base language and instances of few-shot learning problems,…
Languages with Decidable Learning: A Meta-theorem
Paul Krogmeier, P. Madhusudan
We study expression learning problems with syntactic restrictions and introduce the class of finite-aspect checkable languages to characterize symbolic languages that admit decidab…
Learning Formulas in Finite Variable Logics
Paul Krogmeier, P. Madhusudan
We consider grammar-restricted exact learning of formulas and terms in finite variable logics. We propose a novel and versatile automata-theoretic technique for solving such proble…
Deciding Accuracy of Differential Privacy Schemes
Gilles Barthe, Rohit Chadha, Paul Krogmeier +2
Differential privacy is a mathematical framework for developing statistical computations with provable guarantees of privacy and accuracy. In contrast to the privacy component of d…
Decidable Synthesis of Programs with Uninterpreted Functions
Paul Krogmeier, Umang Mathur, Adithya Murali +2
We identify a decidable synthesis problem for a class of programs of unbounded size with conditionals and iteration that work over infinite data domains. The programs in our class…
Composing Neural Learning and Symbolic Reasoning with an Application to Visual Discrimination
Adithya Murali, Atharva Sehgal, Paul Krogmeier +1
We consider the problem of combining machine learning models to perform higher-level cognitive tasks with clear specifications. We propose the novel problem of Visual Discriminatio…
Deciding Memory Safety for Single-Pass Heap-Manipulating Programs
Umang Mathur, Adithya Murali, Paul Krogmeier +2
We investigate the decidability of automatic program verification for programs that manipulate heaps, and in particular, decision procedures for proving memory safety for them. We…