On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,051 papers · 148 categories

Trend · papers per month

count % of corpus

5 results for “Krasulina”

Convergence Rate of Krasulina Estimatorstat.ML

This paper proves the convergence rate of Krasulina's estimator for least eigenvalue and eigenvector.

problem Finding the least eigenvalue and eigenvector of an unknown covariance matrix.

method Developed a convergence proof for Krasulina's estimator.

result Established the convergence rate of Krasulina's estimator for the least eigenvalue and eigenvector.

PCA Eigenvalue Eigenvector Krasulina Convergence

2018-08-28abs ↗pdf ↗

Exponentially convergent stochastic k-PCA without variance reductioncs.LG

Matrix Krasulina achieves fast convergence for online k-PCA.

problem Online k-PCA with low-rank data.

method Generalized Krasulina's method for matrix case, without variance reduction.

result Exponential convergence to principal subspace.

k-PCA Matrix Krasulina Exponential convergence Low-rank data Online learning

2019-04-03abs ↗pdf ↗

Distributed Stochastic Algorithms for High-rate Streaming Principal Component Analysiscs.LG

Paper proposes a distributed method to estimate principal eigenvector from high-rate streaming data.

problem Estimating principal eigenvector from high streaming data rate.

method Distributed Krasulina (D-Krasulina) and mini-batch extension (DM-Krasulina) methods.

result Achieves optimal estimation error rates under high streaming conditions.

Principal Component Analysis Distributed Algorithms Streaming Data Eigenvector Estimation High Rate

2020-01-04abs ↗pdf ↗

An Implicit Form of Krasulina's k-PCA Update without the Orthonormality Constraintcs.LG

New implicit Krasulina's k-PCA update avoids QR-decomposition and improves convergence.

problem Online k-PCA problem with orthonormality constraint.

method Derived an implicit form of Krasulina's update that bypasses orthonormality constraint.

result The new update avoids costly QR-decomposition and yields superior convergence.

k-PCA online learning implicit update Stiefel manifold EM algorithm

2019-09-11abs ↗pdf ↗

The Fast Convergence of Incremental PCAcs.LG

We consider a situation in which we see samples in $\mathbb{R}^d$ drawn i.i.d. from some distribution with mean zero and unknown covariance A. We wish to compute the top eigenvector of A in an incremental fashion - with an algorithm that maintains an estimate of the top eigenvector in O(d) space, and incrementally adju…

2015-01-15abs ↗pdf ↗