Timezone: »

 
Poster
Supervising Unsupervised Learning
Vikas Garg · Adam Kalai

Tue Dec 04 02:00 PM -- 04:00 PM (PST) @ Room 517 AB #164
in Tue Poster Session B »

We introduce a framework to transfer 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 rigorous agnostic bounds on a variety of 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 Kleinberg's impossibility result. Experiments across hundreds of problems demonstrate improvements in performance on unsupervised data with simple algorithms despite the fact our problems come from heterogeneous domains. Additionally, our framework lets us leverage deep networks to learn common features across many small datasets, and perform zero shot learning.

Keywords: Unsupervised Learning · AutoML
[ Paper] 

Author Information

Vikas Garg (MIT)
Adam Kalai (Microsoft Research New England (-(-_(-_-)_-)-))

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors