Wrapper of condSmacof, which finds a low-dimensional embedding of a given distance/dissimilarity matrix, conditioning on available manifold information.
condMDS(d, V, u.dim, W,
method = c('matrix', 'vector'), exact = TRUE,
it.max = 1000, gamma = 1e-05,
init = c('none', 'eigen', 'user'),
U.start, B.start)the embedding result.
the estimated B matrix.
Normalized conditional stress value.
the conditional stress value at each iteration.
the value of the init argument.
the starting values for the embedding.
starting values for the B matrix.
the value of the method argument.
the value of the exact argument.
a distance/dissimilarity matrix of N entities (or a dist object).
an Nxq matrix of q manifold auxiliary parameter values of the N entities.
the embedding dimension.
an NxN symmetric weight matrix. If not given, a matrix of ones will be used.
if matrix, there are no restrictions for the B matrix . If vector, the B matrix is restricted to be diagonal. The latter is more efficient for large q.
only relevant if W is not given. In this case, if exact == FALSE, U is updated by the large-N approximation formula.
the max number of conditional SMACOF iterations.
conditional SMACOF stops early if the reduction of normalized conditional stress is less than gamma
initialization method.
user-defined starting values for the embedding (when init = 'user')
starting B matrix.
Anh Tuan Bui
Bui, A.T. (2021). Dimension Reduction with Prior Information for Knowledge Discovery. arXiv:2111.13646. https://arxiv.org/abs/2111.13646.
Bui, A. T. (2022). A Closed-Form Solution for Conditional Multidimensional Scaling. Pattern Recognition Letters 164, 148-152. https://doi.org/10.1016/j.patrec.2022.11.007
condSmacof, condMDSeigen, condIsomap