On partially blind learning complexity

Joel Ratsaby, Santosh S. Venkatesh

Research output: Contribution to journalConference articlepeer-review


We call a learning environment partially blind when there is an admixture of supervised and unsupervised (or blind) learning. Such situations typically arise in practice when supervised training data labelled by a teacher are scarce or expensive and are supplemented by inexpensive unlabelled (or blind) data available in relative profusion. Vapnik-Cervonenkis theory can be deployed in such settings to quantify the relative worth of supervision (and the lack thereof) in learning. We illustrate the nature of the tradeos possible in a simple setting of hyperplane decision functions and make explicit the role of dimensionality and side-information in these tradeos in the context of d-variate Gaussian mixtures.

Original languageEnglish
Pages (from-to)II-765-II-768
JournalProceedings - IEEE International Symposium on Circuits and Systems
StatePublished - 1 Jan 2000
Externally publishedYes
EventProceedings of the IEEE 2000 International Symposium on Circuits and Systems, ISCAS 2000 - Geneva, Switz, Switzerland
Duration: 28 May 200031 May 2000

ASJC Scopus subject areas

  • Electrical and Electronic Engineering


Dive into the research topics of 'On partially blind learning complexity'. Together they form a unique fingerprint.

Cite this