Synthesizing Machine Learning Programs with PAC Guarantees via Statistical Sketching
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.
Code (0)
등록된 구현이 없습니다.
Tasks
BIG-bench Machine LearningClassificationimage-classificationImage ClassificationLearning TheorySimilar Papers 제목 키워드 기반
PAC Synthesis of Machine Learning Programs
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-…
BIG-bench Machine Learningimage-classificationImage ClassificationLearning TheoryCommunity Detection with a Subsampled Semidefinite Program
Semidefinite programming is an important tool to tackle several problems in data science and signal processing, including clustering and community detection. However, semidefinite programs are often slow in practice, so …
ClusteringCommunity DetectionStochastic Block ModelDeTikZify: Synthesizing Graphics Programs for Scientific Figures and Sketches with TikZ
Creating high-quality scientific figures can be time-consuming and challenging, even though sketching ideas on paper is relatively easy. Furthermore, recreating existing figures that are not stored in formats preserving …
Language ModelingLanguage ModellingRevisiting RIP guarantees for sketching operators on mixture models
In the context of sketching for compressive mixture modeling, we revisit existing proofs of the Restricted Isometry Property of sketching operators with respect to certain mixtures models. After examining the shortcoming…
Asymmetric compressive learning guarantees with applications to quantized sketches
The compressive learning framework reduces the computational cost of training on large-scale datasets. In a sketching phase, the data is first compressed to a lightweight sketch vector, obtained by mapping the data sampl…