Turaco: Complexity-Guided Data Sampling for Training Neural Surrogates of Programs

A Renda, Y Ding, M Carbin - Proceedings of the ACM on Programming …, 2023 - dl.acm.org
Programmers and researchers are increasingly developing surrogates of programs, models
of a subset of the observable behavior of a given program, to solve a variety of software …

Learning to Compile Programs to Neural Networks

L Weber, J Michel, A Renda, M Carbin - arXiv preprint arXiv:2407.15078, 2024 - arxiv.org
A $\textit {neural surrogate of a program} $ is a neural network that mimics the behavior of a
program. Researchers have used these neural surrogates to automatically tune program …

Renamer: A Transformer Architecture In-variant to Variable Renaming

Z Ankner, A Renda, M Carbin - 2023 - openreview.net
Modeling tasks often take inputs from languages including programming languages and
natural language. Many such tasks involve learning functions which are invariant to certain …

Program Inference and Regeneration via Active Learning

J Shen - 2022 - dspace.mit.edu
Software now plays a central role in numerous aspects of human society. Current software
development practices involve significant developer effort in all phases of the software life …

[PDF][PDF] NEURAL ABSTRACT INTERPRETATION: LEVERAGING NEURAL NETWORKS FOR AUTOMATED, EFFICIENT AND DIFFERENTIABLE ABSTRACT …

S GOMBER - 2024 - ggndpsngh.github.io
Abstract Interpretation is a popular technique for formally analyzing the properties of
programs, neural networks, and complex real-world systems. However, designing efficient …

Optimal Data Sampling for Training Neural Surrogates of Programs

A Renda, Y Ding, M Carbin - openreview.net
Programmers and researchers are increasingly developing surrogates of programs, models
of a subset of the observable behavior of a given program, to solve a variety of software …