Synthesizing Machine Learning Programs with PAC Guarantees via Statistical Sketching
arXiv:2110.05390
Abstract
We study the problem of synthesizing programs that include machine learning components such as deep neural networks (DNNs). We focus on statistical properties, which are properties expected to hold with high probability -- e.g., that an image classification model correctly identifies people in images with high probability. We propose novel algorithms for sketching and synthesizing such programs by leveraging ideas from statistical learning theory to provide statistical soundness guarantees. We evaluate our approach on synthesizing list processing programs that include DNN components used to process image inputs, as well as case studies on image classification and on precision medicine. Our results demonstrate that our approach can be used to synthesize programs with probabilistic guarantees.
References in corpus (6)
- Optimization and Abstraction: A Synergistic Approach for Analyzing Neural Network Robustness
- Conformalized Quantile Regression
- Differentiable Programs with Neural Libraries
- PAC Confidence Sets for Deep Neural Networks via Calibrated Prediction
- PAC Confidence Predictions for Deep Neural Network Classifiers
- Learning Neurosymbolic Generative Models via Program Synthesis