Year: 2015
Type: conference-paper
Abstract: 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 surro-gates 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 convex 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. As a result, we have developed the first tractable convex surrogates in the literature for sub-modular losses. We demonstrate the utility of this novel convex surrogate through a real world image labeling task.
Source: HAL
Authors: Yu, Jiaqian, Blaschko, Matthew
Institutions: École Centrale Paris, CentraleSupélec, Centre de Vision Numérique
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W1863660263