SCIENCE@home

Supervising Unsupervised Learning

Vikas K. Garg,A. Kalai

Published 2017 in Neural Information Processing Systems

ABSTRACT

We introduce a framework to leverage knowledge acquired from a repository of (heterogeneous) supervised datasets to new unsupervised datasets. Our perspective avoids the subjectivity inherent in unsupervised learning by reducing it to supervised learning, and provides a principled way to evaluate unsupervised algorithms. We demonstrate the versatility of our framework via simple agnostic bounds on unsupervised problems. In the context of clustering, our approach helps choose the number of clusters and the clustering algorithm, remove the outliers, and provably circumvent the Kleinberg's impossibility result. Experimental results across hundreds of problems demonstrate improved performance on unsupervised data with simple algorithms, despite the fact that our problems come from heterogeneous domains. Additionally, our framework lets us leverage deep networks to learn common features from many such small datasets, and perform zero shot learning.

PUBLICATION RECORD

  • Publication year

    2017

  • Venue

    Neural Information Processing Systems

  • Publication date

    2017-09-14

  • Fields of study

    Mathematics, Computer Science

  • Identifiers
    arXiv 1709.05262
  • External record

    Open on Semantic Scholar

  • Source metadata

    Semantic Scholar

CITATION MAP

EXTRACTION MAP

CLAIMS

  • No claims are published for this paper.

CONCEPTS

  • No concepts are published for this paper.

REFERENCES

Showing 1-30 of 30 references · Page 1 of 1

CITED BY

Showing 1-31 of 31 citing papers · Page 1 of 1