← Back to papers
2008 JMLR JMLR 2008

Learning Similarity with Operator-valued Large-margin Classifiers

Abstract

A method is introduced to learn and represent similarity with linear operators in kernel induced Hilbert spaces. Transferring error bounds for vector valued large-margin classifiers to the setting of Hilbert-Schmidt operators leads to dimension free bounds on a risk functional for linear representations and motivates a regularized objective functional. Minimization of this objective is effected by a simple technique of stochastic gradient descent. The resulting representations are tested on transfer problems in image processing, involving plane and spatial geometric invariants, handwritten characters and face recognition. [abs] [ pdf ][ bib ] © JMLR 2008. (edit, beta)

🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Robotics, Speech & Audio
📈 Trend Setter — Transfer Learning
🧭 Keyword Pioneer — operator-valued classifier
🐣 Hot Topic Early Bird — metric learning

Authors

Andreas Maurer

Topics

Machine Learning > Core Methods > Classification Machine Learning > Core Methods > Metric Learning Machine Learning > Learning Types > Transfer Learning

Keywords

metric learning transfer learning similarity learning face recognition large margin classification hilbert space kernel methods operator-valued classifier
Download PDF

Related papers

On the Equivalence of Linear Dimensionality-Reducing Transformations 2008
Near-Optimal Sensor Placements in Gaussian Processes: Theory, Efficient Algorithms and Empirical Studies 2008
Algorithms for Sparse Linear Classifiers in the Massive Data Setting 2008
Graphical Methods for Efficient Likelihood Inference in Gaussian Covariance Models 2008
Shark 2008