← Back to papers
2009 NIPS NeurIPS 2009

Manifold Regularization for SIR with Rate Root-n Convergence

Abstract

In this paper, we study the manifold regularization for the Sliced Inverse Regression (SIR). The manifold regularization improves the standard SIR in two aspects: 1) it encodes the local geometry for SIR and 2) it enables SIR to deal with transductive and semi-supervised learning problems. We prove that the proposed graph Laplacian based regularization is convergent at rate root-n. The projection directions of the regularized SIR are optimized by using a conjugate gradient method on the Grassmann manifold. Experimental results support our theory.

🧭 Keyword Pioneer — root-n convergence
🐣 Hot Topic Early Bird — semi-supervised learning
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Machine Learning, Mathematics & Optimization, Natural Language Processing, Robotics, Speech & Audio

Authors

Wei Bian , Dacheng Tao

Topics

Machine Learning > Core Methods > Representation Learning Machine Learning > Learning Types > Semi-Supervised Learning Machine Learning > Core Methods > Dimensionality Reduction Machine Learning > Bayesian & Probabilistic > Bayesian Inference

Keywords

dimensionality reduction semi-supervised learning manifold regularization sliced inverse regression root-n convergence grassmann manifold
Download PDF

Related papers

Solving Stochastic Games 2009
Bilinear classifiers for visual recognition 2009
Zero-shot Learning with Semantic Output Codes 2009
Matrix Completion from Power-Law Distributed Samples 2009
Heavy-Tailed Symmetric Stochastic Neighbor Embedding 2009