paper-with-me

Papers

Synthesizing Machine Learning Programs with PAC Guarantees via Statistical Sketching

2021-10-11 · Osbert Bastani

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.

📄 PDF Abstract BibTeX arXiv:2110.05390

Code (0)

등록된 구현이 없습니다.

Tasks

BIG-bench Machine LearningClassificationimage-classificationImage ClassificationLearning Theory

Similar Papers 제목 키워드 기반

PAC Synthesis of Machine Learning Programs

2021-10-08 · NeurIPS Workshop AIPLANS 2021 12 · Osbert Bastani

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 Theory

Community Detection with a Subsampled Semidefinite Program

2021-02-02 · Pedro Abdalla, Afonso S. Bandeira

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 Model

DeTikZify: Synthesizing Graphics Programs for Scientific Figures and Sketches with TikZ

2024-05-24 · Jonas Belouadi, Simone Paolo Ponzetto, Steffen Eger

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 Modelling

Revisiting RIP guarantees for sketching operators on mixture models

2023-12-09 · Ayoub Belhadji, Rémi Gribonval

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

2021-04-20 · Vincent Schellekens, Laurent Jacques

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…