Fast learning rates with heavy-tailed losses

09/29/2016
by   Vu Dinh, et al.
0

We study fast learning rates when the losses are not necessarily bounded and may have a distribution with heavy tails. To enable such analyses, we introduce two new conditions: (i) the envelope function _f ∈F|ℓ∘ f|, where ℓ is the loss function and F is the hypothesis class, exists and is L^r-integrable, and (ii) ℓ satisfies the multi-scale Bernstein's condition on F. Under these assumptions, we prove that learning rate faster than O(n^-1/2) can be obtained and, depending on r and the multi-scale Bernstein's powers, can be arbitrarily close to O(n^-1). We then verify these assumptions and derive fast learning rates for the problem of vector quantization by k-means clustering with heavy-tailed distributions. The analyses enable us to obtain novel learning rates that extend and complement existing results in the literature from both theoretical and practical viewpoints.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset