Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

10

EVOW
2010
Springer

favoriteEmaildiscussreport

149views Artificial Intelligence» more EVOW 2010»

Adaptive Noisy Optimization

13 years 11 months ago

Adaptive Noisy Optimization

Download hal.archives-ouvertes.fr

In this paper, adaptive noisy optimization on variants of the noisy sphere model is considered, i.e. optimization in which the same algorithm is able to adapt to several frameworks, including some for which no bound has never been derived. Incidentally, bounds derived by [16] for noise quickly decreasing to zero around the optimum are extended to the more general case of a positively lower-bounded noise thanks to a careful use of Bernstein bounds (using empirical estimates of the variance) instead of Chernoﬀ-like variants.

Philippe Rolet, Olivier Teytaud

Real-time Traffic

Adaptive Noisy Optimization | Artificial Intelligence | EVOW 2010 | Lower-bounded Noise Thanks | Noisy Sphere Model |

claim paper

Related Content

» Distributed Adaptive Particle Swarm Optimizer in Dynamic Environment

» Adaptive Sampling for Noisy Problems

» Benchmarking the 11CMAES on the BBOB2009 noisy testbed

» NearOptimal Bayesian Active Learning with Noisy Observations

» AMaLGaM IDEAs in noisy blackbox optimization benchmarking

» On the adaptation of noise level for stochastic optimization

» On Distributed Computation in Noisy Random Planar Networks

» Adaptive optimisation of noisy blackbox functions inherent in microscopic models

» Phase Local Approximation PhaseLa Technique for Phase Unwrap From Noisy Data

Post Info
More Details (n/a)

Added	28 May 2010
Updated	28 May 2010
Type	Conference
Year	2010
Where	EVOW
Authors	Philippe Rolet, Olivier Teytaud

Comments (0)