Adaptive Online Prediction by Following the Perturbed Leader
When applying aggregating strategies to Prediction with Expert Advice (PEA), the learning rate must be adaptively tuned. The natural choice of √complexity/current loss renders the analysis of Weighted Majority (WM) derivatives quite complicated. In part
|Collections||ANU Research Publications|
|Source:||Journal of Machine Learning Research|
|01_Hutter_Adaptive_Online_Prediction_by_2005.pdf||329.61 kB||Adobe PDF||Request a copy|
Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.