Revunova E.G.
Linear model selection criteria for the solution of discrete ill-posed problems on the basis of singular value decomposition and random projection

Criteria are developed to determine the optimal number of components of a linear model in solving a discrete ill-posed problem by the methods of truncated singular value decomposition and random projection. To this end, the behavior of dependencies of the error vector of the solution and the restoration error of the vector of the right side on the model dimensionality and their minima is investigated. An experimental investigation of the developed criteria was also pursued and its results are provided. © 2016, Springer Science+Business Media New York.

Keywords: discrete ill-posed problem, model selection criteria, random projection, truncated singular value decomposition, Euler equations, Experimental investigations, Ill posed problem, Linear modeling, Model selection criteria, Random projections, Restoration errors, Singular decomposition, Truncated singular value decomposition, Singular value decomposition

Cite:
Revunova E.G. (2016). Linear model selection criteria for the solution of discrete ill-posed problems on the basis of singular value decomposition and random projection. Cybernetics and Systems Analysis, 52 (4), 174-192. doi: https://doi.org/10.1007/s10559-016-9868-4 http://jnas.nbuv.gov.ua/article/UJRN-0001294516 [In Russian].