Non-convex optimization on stiefel manifold and applications to machine learning

Authors:
Takafumi Kanamori;Akiko Takeda
Affiliations:
Nagoya University, Nagoya-shi, Aichi, Japan;Keio University, Yokohama, Kanagawa, Japan
Venue:
ICONIP'12 Proceedings of the 19th international conference on Neural Information Processing - Volume Part I
Year:
2012

Citing 7
Cited 0

The Geometry of Algorithms with Orthogonality Constraints

SIAM Journal on Matrix Analysis and Applications
Learning algorithms utilizing quasi-geodesic flows on the Stiefel manifold

Neurocomputing
Direct density-ratio estimation with dimensionality reduction via least-squares hetero-distributional subspace search

Neural Networks
Optimization for Machine Learning

Optimization for Machine Learning
Statistical analysis of kernel-based least-squares density-ratio estimation

Machine Learning
Density Ratio Estimation in Machine Learning

Density Ratio Estimation in Machine Learning
Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers

Foundations and Trends® in Machine Learning

Quantified Score

Hi-index	0.00

Visualization

Abstract

We study non-convex optimization problems which appear in machine learning and statistics. Recently, convexity became an important feature to develop high-performance learning algorithms. On the other hand, non-convex optimization is also required in machine learning. In this paper, especially we deal with non-convex optimization problems on the Stiefel manifold. The Stiefel manifold consists of rectangular matrices, and many important problems in machine learning can be expressed in this framework. We compare some non-linear optimization methods which are applicable to machine learning algorithms.