Optimal Program Synthesis via Abstract Interpretation
S Mell, S Zdancewic, O Bastani - Proceedings of the ACM on …, 2024 - dl.acm.org
We consider the problem of synthesizing programs with numerical constants that optimize a
quantitative objective, such as accuracy, over a set of input-output examples. We propose a …
quantitative objective, such as accuracy, over a set of input-output examples. We propose a …
{MadEye}: Boosting Live Video Analytics Accuracy with Adaptive Camera Configurations
Camera orientations (ie, rotation and zoom) govern the content that a camera captures in a
given scene, which in turn heavily influences the accuracy of live video analytics pipelines …
given scene, which in turn heavily influences the accuracy of live video analytics pipelines …
Uncertainty Quantification for Neurosymbolic Programs via Compositional Conformal Prediction
Machine learning has become an effective tool for automatically annotating unstructured
data (eg, images) with structured labels (eg, object detections). As a result, a new …
data (eg, images) with structured labels (eg, object detections). As a result, a new …