optimize_epoch

matrix with embedding coordinates (coordinates along columns)

embedding

matrix with rows: from to; indexes must be 0-based

pairs

vector with 0/1 whether to adjust or not

adjust

vector with negative-neighbors-set size

vector with configuration parameters, a, b, gamma, move_other

numeric learning rate for this epoch

alpha

matrix with columns: eps, epns, eon2s, eons, nns (in that order)

book

run one epoch of the umap optimization

internal

Uniform manifold approximation and projection is a technique
for dimension reduction. The algorithm was described by McInnes and
Healy (2018) in <arXiv:1802.03426>. This package provides an interface
for two implementations. One is written from scratch, including components
for nearest-neighbor search and for embedding. The second implementation
is a wrapper for 'python' package 'umap-learn' (requires separate
installation, see vignette for more details).

optimize_epoch: run one epoch of the umap optimization

Description

Usage

Arguments