Physics – Condensed Matter – Statistical Mechanics
Scientific paper
2011-12-22
Physics
Condensed Matter
Statistical Mechanics
5 pag., 2 fig
Scientific paper
We compute analytically, for large $N$, the probability $\mathcal{P}(N_+,N)$ that a $N\times N$ Wishart random matrix has $N_+$ eigenvalues exceeding a threshold $N\zeta$, including its large deviation tails. This probability plays a benchmark role when performing the Principal Component Analysis of a large empirical dataset. We find that $\mathcal{P}(N_+,N)\approx\exp(-\beta N^2 \psi_\zeta(N_+/N))$, where $\beta$ is the Dyson index of the ensemble and $\psi_\zeta(\kappa)$ is a rate function that we compute explicitly in the full range $0\leq \kappa\leq 1$ and for any $\zeta$. The rate function $\psi_\zeta(\kappa)$ displays a quadratic behavior modulated by a logarithmic singularity close to its minimum $\kappa^\star(\zeta)$. This is shown to be a consequence of a phase transition in an associated Coulomb gas problem. The variance $\Delta(N)$ of the number of relevant components is also shown to grow universally (independent of $\zeta)$ as $\Delta(N)\sim (\beta \pi^2)^{-1}\ln N$ for large $N$.
Majumdar Satya N.
Vivo Pierpaolo
No associations
LandOfFree
Number of relevant directions in Principal Component Analysis and Wishart random matrices does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Number of relevant directions in Principal Component Analysis and Wishart random matrices, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Number of relevant directions in Principal Component Analysis and Wishart random matrices will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-307969