betaFeedback

WorksComputer Science

A Fast Algorithm for the Familywise Loss

Abstract

The familywise (FW) loss for multiclass classification, introduced by Duchi, Ruan, and Khosravi, achieves universal equivalence to the 0-1 loss, and thus has stronger theoretical properties than cross entropy (CE). Prior work, however, left open whether FW is as computationally efficient as CE. First, on the theoretical side, we prove that the FW gradient can be computed in O(K)O(K) time, where KK is the number of classes. Second, on the practical side, we develop optimized kernels for computing the forward and backward passes of FW which outperform CE in terms of speed on both CPU and GPU.

Paper details

vlnc:W_z38kr9dr
Version
v1 · latest
Published
Fresh — added to the Hub within the last 30 days
Added
License
CC-BY-NC-SA-4.0
Usage

views · 0

downloads · 0

A view counts once per browser per day, a download each time the PDF is requested.

  • Computer Science

generative AI tools

View statement
Looking for related papers…