Learning algorithms utilizing quasi-geodesic flows on the Stiefel manifold

  title={Learning algorithms utilizing quasi-geodesic flows on the Stiefel manifold},
  author={Yasunori Nishimori and Shotaro Akaho},
In this paper we extend the natural gradient method for neural networks to the case where the weight vectors are constrained to the Stiefel manifold. The proposed methods involve numerical integration techniques of the gradient flow without violating the manifold constraints. The extensions are based on geodesics. We rigorously formulate the previously proposed natural gradient and geodesics on the manifold exploiting the fact that the Stiefel manifold is a homogeneous space having a transitive… CONTINUE READING
Highly Influential
This paper has highly influenced 10 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 179 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 68 extracted citations

Robust Independent Component Analysis via Minimum $\gamma $-Divergence Estimation

IEEE Journal of Selected Topics in Signal Processing • 2013
View 4 Excerpts
Highly Influenced

Interference alignment for multi-user MIMO interference channels via a Riemannian optimization approach

2015 IEEE 26th Annual International Symposium on Personal, Indoor, and Mobile Radio Communications (PIMRC) • 2015
View 4 Excerpts
Highly Influenced

179 Citations

Citations per Year
Semantic Scholar estimates that this publication has 179 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 26 references

Similar Papers

Loading similar papers…