Regularized least square regression with unbounded and dependent sampling (Q369717): Difference between revisions
From MaRDI portal
Changed an Item |
Created claim: Wikidata QID (P12): Q58915348, #quickstatements; #temporary_batch_1704736726153 |
||
Property / Wikidata QID | |||
Property / Wikidata QID: Q58915348 / rank | |||
Normal rank |
Revision as of 20:00, 8 January 2024
scientific article
Language | Label | Description | Also known as |
---|---|---|---|
English | Regularized least square regression with unbounded and dependent sampling |
scientific article |
Statements
Regularized least square regression with unbounded and dependent sampling (English)
0 references
19 September 2013
0 references
Summary: This paper mainly focuses on the least square regression problem for \(\alpha\)-mixing and \(\phi\)-mixing processes. The standard bound assumption for output data is abandoned and the learning algorithm is implemented with samples drawn from a dependent sampling process with a more general output data condition. Capacity independent error bounds and learning rates are deduced by means of the integral operator technique.
0 references