pith. sign in

arxiv: 1712.02111 · v2 · pith:SQJ4QRSHnew · submitted 2017-12-06 · 🧮 math.NA · cs.NA

Stochastic subspace correction in Hilbert space

classification 🧮 math.NA cs.NA
keywords hilbertspacesalgorithmsapproxapproximationcollectionconditionsconnection
0
0 comments X
read the original abstract

We consider an incremental approximation method for solving variational problems in infinite-dimensional Hilbert spaces, where in each step a randomly and independently selected subproblem from an infinite collection of subproblems is solved. we show that convergence rates for the expectation of the squared error can be guaranteed under weaker conditions than previously established in [Constr. Approx. 44:1 (2016), 121-139]. A connection to the theory of learning algorithms in reproducing kernel Hilbert spaces is revealed.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.