Density-Sensitive Semisupervised Inference

Details Density-Sensitive Semisupervised Inference Density-Sensitive Semisupervised Inference

2012-04-07

arxiv.org/abs/1204.1685v1

Mathematics

Statistics Theory

This is a significant extension of the work in 1111.6410 by the same authors

Scientific paper

Semisupervised methods are techniques for using labeled data $(X_1,Y_1),..., (X_n,Y_n)$ together with unlabeled data $X_{n+1},..., X_N$ to make predictions. These methods invoke some assumption that links the marginal distribution $P_X$ of $X$ to the regression function $f(x)$. For example, it is common to assume that $f$ is very smooth over high density regions of $P_X$. Many of the methods are ad-hoc and have been shown to work in specific examples but are lacking a theoretical foundation. We provide a minimax framework for analyzing semisupervised methods. In particular, we study methods based on metrics that are sensitive to the distribution $P_X$. Our model includes a parameter $\alpha$ that controls the strength of the semisupervised assumption. We then use the data to adapt to $\alpha$.

Affiliated with

Also associated with

No associations

Rating

Density-Sensitive Semisupervised Inference does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Density-Sensitive Semisupervised Inference, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Density-Sensitive Semisupervised Inference will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-509063