| Autor: |
Rolet, Philippe, Teytaud, Olivier |
| Zdroj: |
Learning & Intelligent Optimization (9783642137990); 2010, p97-110, 14p |
| Abstrakt: |
We show complexity bounds for noisy optimization, in frameworks in which noise is stronger than in previously published papers[19]. We also propose an algorithm based on bandits (variants of [16]) that reaches the bound within logarithmic factors. We emphasize the differences with empirical derived published algorithms. Complete mathematical proofs can be found in [26]. [ABSTRACT FROM AUTHOR] |
| Databáze: |
Complementary Index |
| Externí odkaz: |
|
