mlsanityData to 14 Oct 2026

Synthesizing Machine Learning Programs with PAC Guarantees via Statistical Sketching

arXiv 2110.05390 ↗First posted 11 Oct 2021cs.PL cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 33 of its 76 references that are in the map. First posted on arXiv 11 Oct 2021.

Builds on

33 of 76 references.

References · 33

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  4. 2015End-to-End Training of Deep Visuomotor Policiescited by 875
  5. 2017Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networkscited by 744
  6. 2019Conformalized Quantile Regressioncited by 629
  7. 2017BranchyNet: Fast Inference via Early Exiting from Deep Neural Networkscited by 596
  8. 2019Conformal Prediction Under Covariate Shiftcited by 519
  9. 2020Uncertainty Sets for Image Classifiers using Conformal Predictioncited by 366
  10. 2016Safety Verification of Deep Neural Networkscited by 263
  11. 2018Programmatically Interpretable Reinforcement Learningcited by 193
  12. 2017The Case for Learned Index Structurescited by 188
21 more
  1. 2018Verifiable Reinforcement Learning via Policy Extractioncited by 177
  2. 2017Adaptive Neural Networks for Efficient Inferencecited by 163
  3. 2016Measuring Neural Net Robustness with Constraintscited by 90
  4. 2018Verisig: verifying safety properties of hybrid systems with neural network controllerscited by 84
  5. 2018Scenic: A Language for Scenario Specification and Scene Generationcited by 83
  6. 2018Scalable End-to-End Autonomous Vehicle Testing via Rare-event Simulationcited by 77
  7. 2017Learning to Infer Graphics Programs from Hand-Drawn Imagescited by 74
  8. 2019PAC Confidence Sets for Deep Neural Networks via Calibrated Predictioncited by 60
  9. 2019Adaptive, Distribution-Free Prediction Intervals for Deep Networkscited by 56
  10. 2020Neurosymbolic Reinforcement Learning with Formally Verified Explorationcited by 49
  11. 2018Probabilistic Verification of Fairness Properties via Concentrationcited by 45
  12. 2019Optimization and Abstraction: A Synergistic Approach for Analyzing Neural Network Robustnesscited by 40
  13. 2019An Inductive Synthesis Framework for Verifiable Reinforcement Learningcited by 39
  14. 2018HOUDINI: Lifelong Learning as Program Synthesiscited by 38
  15. 2020Learning Differentiable Programs with Admissible Neural Heuristicscited by 32
  16. 2016Differentiable Programs with Neural Librariescited by 30
  17. 2020PAC Confidence Predictions for Deep Neural Network Classifierscited by 21
  18. 2019Bayesian Synthesis of Probabilistic Programs for Automatic Data Modelingcited by 19
  19. 2019Learning Neurosymbolic Generative Models via Program Synthesiscited by 11
  20. 2019A Programmatic and Semantic Approach to Explaining and DebuggingNeural Network Based Object Detectorscited by 11
  21. 2019Efficient Synthesis with Probabilistic Constraintscited by 2

Built on by

Not cited yet.