The Lovász Hinge: A Novel Convex Surrogate for Submodular Losses - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Preprints, Working Papers, ... Year : 2017

The Lovász Hinge: A Novel Convex Surrogate for Submodular Losses


Learning with non-modular losses is an important problem when sets of predictions are made simultaneously. The main tools for constructing convex surrogate loss functions for set prediction are margin rescaling and slack rescaling. In this work, we show that these strategies lead to tight convex surrogates iff the underlying loss function is increasing in the number of incorrect predictions. However, gradient or cutting-plane computation for these functions is NP-hard for non-supermodular loss functions. We propose instead a novel surrogate loss function for submodular losses, the Lovász hinge, which leads to O(p log p) complexity with O(p) oracle accesses to the loss function to compute a gradient or cutting-plane. We prove that the Lovász hinge is convex and yields an extension. As a result, we have developed the first tractable convex surrogates in the literature for submodular losses. We demonstrate the utility of this novel convex surrogate through several set prediction tasks, including on the PASCAL VOC and Microsoft COCO datasets.
Fichier principal
Vignette du fichier
arXiv2017v2.pdf (1.19 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01241626 , version 1 (10-12-2015)
hal-01241626 , version 2 (15-05-2017)



Jiaqian Yu, Matthew Blaschko. The Lovász Hinge: A Novel Convex Surrogate for Submodular Losses. 2017. ⟨hal-01241626v2⟩
508 View
954 Download



Gmail Facebook X LinkedIn More