On aggregation for heavy-tailed classes
We introduce an alternative to the notion of ‘fast rate’ in Learning Theory, which coincides with the optimal error rate when the given class happens to be convex and regular in some sense. While it is well known that such a rate cannot always be attained by a learning procedure (i.e., a procedure that selects a function in the given class), we introduce an aggregation procedure that attains that rate under rather minimal assumptions—for example, that the Lq and L2 norms are equivalent on the...[Show more]
|Collections||ANU Research Publications|
|Source:||Probability Theory and Related Fields|
|01_Mendelson_On_aggregation_for_2017.pdf||315.33 kB||Adobe PDF||Request a copy|
|02_Mendelson_On_aggregation_for_2017.pdf||478.01 kB||Adobe PDF||Request a copy|
Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.