Damped Anderson Acceleration with Epsilon Monotonicity for Accelerating EM-Like Monotone Algorithms

Implements the DAAREM method for accelerating the convergence of slow, monotone sequences from smooth, fixed-point iterations such as the EM algorithm. For further details about the DAAREM method. see Henderson, N.C. and Varadhan, R. (2018) .


Log of changes to SQUAREM

o first release (version 0.2): August 6, 2018

o second release (version 0.3): February, 2019 - fixed a bug in how the default order was determined - fixed code for finding damping parameter; it can now handle the case of one or more singular values that are numerically zero

Reference manual

It appears you don't have a PDF plugin for this browser. You can click here to download the reference manual.


0.4 by Nicholas Henderson, 17 days ago

Browse source code at https://github.com/cran/daarem

Authors: Nicholas Henderson [cre, aut] , Ravi Varadhan [aut]

Documentation:   PDF Manual  

GPL-2 license

Imports stats, utils

See at CRAN