On-line learning of linear functions
| Autor: | Philip M. Long, Manfred K. Warmuth, Nick Littlestone |
|---|---|
| Rok vydání: | 1995 |
| Předmět: |
Sequence
Mathematical optimization Logarithm Wake-sleep algorithm General Mathematics Stability (learning theory) Online machine learning System of linear equations Theoretical Computer Science Computational Mathematics Noise Computational Theory and Mathematics Computational learning theory Applied mathematics Empirical risk minimization Mathematics |
| Zdroj: | STOC |
| ISSN: | 1420-8954 1016-3328 |
| DOI: | 10.1007/bf01277953 |
| Popis: | We present an algorithm for the on-line learning of linear functions which is optimal to within a constant factor with respect to bounds on the sum of squared errors for a worst case sequence of trials. The bounds are logarithmic in the number of variables. Furthermore, the algorithm is shown to be optimally robust with respect to noise in the data (again to within a constant factor). We also discuss an application of our methods to the iterative solution of sparse systems of linear equations. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink