A Convex Surrogate Operator for General Non-Modular Loss Functions - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2016

A Convex Surrogate Operator for General Non-Modular Loss Functions

Abstract

In this work, a novel generic convex surrogate for general non-modular loss functions is introduced, which provides for the first time a tractable solution for loss functions that are neither supermodular nor submodular. This convex surrogate is based on a submodular-supermodular decomposition. It takes the sum of two convex surrogates that separately bound the supermodular component and the submodular component using slack-rescaling and the Lovász hinge, respectively. This surrogate is convex, piecewise linear, an extension of the loss function, and for which subgradient computation is polynomial time. Empirical results are reported on a non-submodular loss based on the Sørensen-Dice difference function demonstrating the improved performance, efficiency, and scalabil-ity of the novel convex surrogate.
Fichier principal
Vignette du fichier
benelearn2016.pdf (242.11 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01417108 , version 1 (15-12-2016)

Identifiers

  • HAL Id : hal-01417108 , version 1

Cite

Jiaqian B Yu, Matthew Blaschko. A Convex Surrogate Operator for General Non-Modular Loss Functions. The 25th Belgian-Dutch Conference on Machine Learning, Sep 2016, Kortrijk, Belgium. ⟨hal-01417108⟩
271 View
68 Download

Share

Gmail Facebook X LinkedIn More