REVIEW 2 cited by
Fast and Simple PCA via Convex Optimization
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
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 $\sqrt{d/N}$.
Forward citations
Cited by 2 Pith papers
-
What is a Sketch-and-Precondition Derivation for Low-Rank Approximation? Inverse Power Error or Inverse Power Estimation?
Sketched inverse iteration applied to the sketching error gives a top-k eigensolver whose convergence rate is proportional to the quality of a Nyström preconditioner and depends only on the final spectral gap.
-
Adaptive Federated Optimization
Proposes federated adaptive optimizers (FedAdagrad, FedAdam, FedYogi) with convergence analysis for non-convex objectives under data heterogeneity and reports empirical gains over FedAvg.
Discussion (0). Continue with ORCID to comment.