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.

168,694 papers · 148 categories

Trend · papers per month

count % of corpus

3 results for “EPCA”

Repulsive Mixture Models of Exponential Family PCA for Clusteringcs.LG

A new model improves clustering by reducing redundancy in mixture of local EPCAs.

problem Redundancy in traditional mixture models causes ambiguity in clustering.

method Introduced a repulsiveness-encouraging prior and a DPP for diversity in DEPCAM model.

result The method reduces model redundancy and improves clustering performance.

clustering mixture models EPCA repulsiveness DPP

2020-04-07abs ↗pdf ↗

Bayesian exponential family projections for coupled data sourcescs.LG

Exponential family extensions of principal component analysis (EPCA) have received a considerable amount of attention in recent years, demonstrating the growing need for basic modeling tools that do not assume the squared loss or Gaussian distribution. We extend the EPCA model toolbox by presenting the first exponentia…

2012-03-15abs ↗pdf ↗

Black-Box

k

-to-

1

-PCA Reductions: Theory and Applicationsmath.NA

New analysis improves black-box $k$ -PCA algorithms, reducing parameter loss.

problem Designing efficient

k

-PCA algorithms with black-box access to a 1-PCA oracle.

method Black-box deflation methods, analyzing ePCA and cPCA approximations.

result Deflation methods suffer no asymptotic parameter loss for

k

-cPCA in feasible regimes.

k-PCA black-box deflation methods approximation parameter loss

2024-03-06abs ↗pdf ↗