Spectral risk-based learning using unbounded losses

Matthew Holland · El Mehdi Haress

[ Abstract ]
Tue 29 Mar 1 a.m. PDT — 2:30 a.m. PDT


In this work, we consider the setting of learning problems under a wide class of spectral risk (or "L-risk") functions, where a Lipschitz-continuous spectral density is used to flexibly assign weight to extreme loss values. We obtain excess risk guarantees for a derivative-free learning procedure under unbounded heavy-tailed loss distributions, and propose a computationally efficient implementation which empirically outperforms traditional risk minimizers in terms of balancing spectral risk and misclassification error.

Chat is not available.