2009 NIPS NeurIPS 2009

Distribution Matching for Transduction

Abstract

Many transductive inference algorithms assume that distributions over training and test estimates should be related, e.g. by providing a large margin of separation on both sets. We use this idea to design a transduction algorithm which can be used without modification for classification, regression, and structured estimation. At its heart we exploit the fact that for a good learner the distributions over the outputs on training and test sets should match. This is a classical two-sample problem which can be solved efficiently in its most general form by using distance measures in Hilbert Space. It turns out that a number of existing heuristics can be viewed as special cases of our approach.

🌉 Interdisciplinary Bridge — Artificial Intelligence and Machine Learning
📈 Trend Setter — Transfer Learning
🧭 Keyword Pioneer — transductive inference
🐝 Cross-Pollinator — Artificial Intelligence, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Machine Learning, Mathematics & Optimization, Speech & Audio
🐣 Hot Topic Early Bird — semi-supervised learning