pith. sign in

arxiv: 1509.05647 · v4 · pith:2IJZTTNMnew · submitted 2015-09-18 · 🧮 math.OC · cs.LG· cs.NA· math.NA

Fast and Simple PCA via Convex Optimization

classification 🧮 math.OC cs.LGcs.NAmath.NA
keywords epsilonlambdaconvexdeltaoptimizationcasecomponentcompute
0
0 comments X
read the original abstract

The problem of principle component analysis (PCA) is traditionally solved by spectral or algebraic methods. We show how computing the leading principal component could be reduced to solving a \textit{small} number of well-conditioned {\it convex} optimization problems. This gives rise to a new efficient method for PCA based on recent advances in stochastic methods for convex optimization. In particular we show that given a $d\times d$ matrix $\X = \frac{1}{n}\sum_{i=1}^n\x_i\x_i^{\top}$ with top eigenvector $\u$ and top eigenvalue $\lambda_1$ it is possible to: \begin{itemize} \item compute a unit vector $\w$ such that $(\w^{\top}\u)^2 \geq 1-\epsilon$ in $\tilde{O}\left({\frac{d}{\delta^2}+N}\right)$ time, where $\delta = \lambda_1 - \lambda_2$ and $N$ is the total number of non-zero entries in $\x_1,...,\x_n$, \item compute a unit vector $\w$ such that $\w^{\top}\X\w \geq \lambda_1-\epsilon$ in $\tilde{O}(d/\epsilon^2)$ time. \end{itemize} To the best of our knowledge, these bounds are the fastest to date for a wide regime of parameters. These results could be further accelerated when $\delta$ (in the first case) and $\epsilon$ (in the second case) are smaller than $\sqrt{d/N}$.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Adaptive Federated Optimization

    cs.LG 2020-02 unverdicted novelty 6.0

    Proposes federated adaptive optimizers (FedAdagrad, FedAdam, FedYogi) with convergence analysis for non-convex objectives under data heterogeneity and reports empirical gains over FedAvg.