Statistical Consistency of Kernel Canonical Correlation Analysis

  title={Statistical Consistency of Kernel Canonical Correlation Analysis},
  author={Kenji Fukumizu and Francis R. Bach and Arthur Gretton},
  journal={Journal of Machine Learning Research},
While kernel canonical correlation analysis (CCA) has been applied in many contexts, the convergence of finite sample estimates of the associated functions to their population counterparts has not yet been established. This paper gives a mathematical proof of the statistical convergence of kernel CCA, providing a theoretical justification for the method. The proof uses covariance operators defined on reproducing kernel Hilbert spaces, and analyzes the convergence of their empirical estimates of… CONTINUE READING
Highly Influential
This paper has highly influenced 12 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS

From This Paper

Figures, tables, and topics from this paper.
92 Citations
28 References
Similar Papers


Publications citing this paper.
Showing 1-10 of 92 extracted citations


Publications referenced by this paper.
Showing 1-10 of 28 references

Canonical correlation analysis when the data are curves

  • Sue E. Leurgans, Rana A. Moyeed, Bernard W. Silverman
  • Journal of the Royal Statistical Society, Series…
  • 1993
Highly Influential
6 Excerpts

The Theory of Tikhonov Regularization for Fredholm Equations of the First Kind

  • Charles W. Groetsch
  • 1984
Highly Influential
3 Excerpts

Detecting hidden synchronization of chaotic dynamical systems: A kernel-based approach

  • Hiromichi Suetani, Yukito Iba, Kazuyuki Aihara
  • Journal of Physics A: Mathematical and General,
  • 2006
2 Excerpts

Similar Papers

Loading similar papers…