Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
Syntax-guided program reduction for understanding neural code intelligence models
MAPS 2022: Proceedings of the 6th ACM SIGPLAN International Symposium on Machine ProgrammingJune 2022, Pages 70–79https://doi.org/10.1145/3520312.3534869Neural code intelligence (CI) models are opaque black-boxes and offer little insight on the features they use in making predictions. This opacity may lead to distrust in their prediction and hamper their wider adoption in safety-critical applications. ...
Automatically debugging AutoML pipelines using maro: ML automated remediation oracle
MAPS 2022: Proceedings of the 6th ACM SIGPLAN International Symposium on Machine ProgrammingJune 2022, Pages 60–69https://doi.org/10.1145/3520312.3534868Machine learning in practice often involves complex pipelines for data cleansing, feature engineering, preprocessing, and prediction. These pipelines are composed of operators, which have to be correctly connected and whose hyperparameters must be ...
- research-articleJune 2022
From perception to programs: regularize, overparameterize, and amortize
MAPS 2022: Proceedings of the 6th ACM SIGPLAN International Symposium on Machine ProgrammingJune 2022, Pages 30–39https://doi.org/10.1145/3520312.3534865Toward combining inductive reasoning with perception abilities, we develop techniques for neurosymbolic program synthesis where perceptual input is first parsed by neural nets into a low-dimensional interpretable representation, which is then processed ...
- research-articleJune 2022
A graph neural network-based performance model for deep learning applications
MAPS 2022: Proceedings of the 6th ACM SIGPLAN International Symposium on Machine ProgrammingJune 2022, Pages 11–20https://doi.org/10.1145/3520312.3534863The unprecedented proliferation of machine learning based software brings an ever-increasing need to optimize the implementation of such applications. State-of-the-art compilers for neural networks, such as Halide and TVM, incorporate a machine learning-...
- research-articleJune 2022
A systematic evaluation of large language models of code
MAPS 2022: Proceedings of the 6th ACM SIGPLAN International Symposium on Machine ProgrammingJune 2022, Pages 1–10https://doi.org/10.1145/3520312.3534862Large language models (LMs) of code have recently shown tremendous promise in completing code and synthesizing code from natural language descriptions. However, the current state-of-the-art code LMs (e.g., Codex) are not publicly available, leaving many ...