Labeled versus unlabeled distributed Cayley networks

Labeled DNA Unlabeled DNA

Learning Privately with Labeled and Unlabeled Examples

A private learner is an algorithm that given a sample of labeled individual examples outputs a generalizing hypothesis while preserving the privacy of each individual. In 2008, Kasiviswanathan et al. (FOCS 2008) gave a generic construction of private learners, in which the sample complexity is (generally) higher than what is needed for non-private learners. This gap in the sample complexity was...

Machine Learning with Labeled and Unlabeled Data

The field of semi-supervised learning has been expanding rapidly in the past few years, with a sheer increase in the number of related publications. In this paper we present the SSL problem in contrast with supervised and unsupervised learning. In addition, we propose a taxonomy with which we categorize many existing approaches described in the literature based on their underlying framework, da...

Ramsey degrees, labeled and unlabeled partitions

Let K be a class of …nite relational structures. Let Kn be the class obtained by adding labeled partition, in at most n many parts, to structures in K. Let EK be the class obtained by adding unlabeled partition, i.e. an equivalence relation, to structures in K. We calculate Ramsey degrees for structures in Kn and EK. In addition we apply our results to dynamics of minimal ‡ows.

Learning with labeled and unlabeled data

In this paper, on the one hand, we aim to give a review on literature dealing with the problem of supervised learning aided by additional unlabeled data. On the other hand, being a part of the author’s first year PhD report, the paper serves as a frame to bundle related work by the author as well as numerous suggestions for potential future work. Therefore, this work contains more speculative a...