4 papers
Emergent Representations of Program Semantics in Language Models Trained on Programs
Charles Jin, Martin Rinard
We present evidence that language models (LMs) of code can learn to represent the formal semantics of programs, despite being trained only to perform next-token prediction. Specifi…
Probabilistic Programming with Programmable Variational Inference
McCoy R. Becker, Alexander K. Lew, Xiaoyan Wang +4
Compared to the wide array of advanced Monte Carlo methods supported by modern probabilistic programming languages (PPLs), PPL support for variational inference (VI) is less develo…
GenSQL: A Probabilistic Programming System for Querying Generative Models of Database Tables
Mathieu Huot, Matin Ghavami, Alexander K. Lew +6
This article presents GenSQL, a probabilistic programming system for querying probabilistic generative models of database tables. By augmenting SQL with only a few key primitives f…
Correlated vs. Uncorrelated Randomness in Adversarial Congestion Team Games
Edan Orzech, Martin Rinard
We consider team zero-sum network congestion games with agents playing against interceptors over a graph . The agents aim to minimize their collective cost of sending tr…