Skip to Main content Skip to Navigation
Conference papers

Marginal Weighted Maximum Log-likelihood for Efficient Learning of Perturb-and-Map models

Abstract : We consider the structured-output prediction problem through probabilistic approaches and generalize the “perturb-and-MAP” framework to more challenging weighted Hamming losses, which are crucial in applications. While in principle our approach is a straightforward marginalization, it requires solving many related MAP inference problems. We show that for log-supermodular pairwise models these operations can be performed efficiently using the machinery of dynamic graph cuts. We also propose to use double stochastic gradient descent, both on the data and on the perturbations, for efficient learning. Our framework can naturally take weak supervision (e.g., partial labels) into account. We conduct a set of experiments on medium-scale character recognition and image segmentation, showing the benefits of our algorithms.
Complete list of metadata
Contributor : Tatiana Shpakova Connect in order to contact the contributor
Submitted on : Thursday, November 29, 2018 - 3:29:10 PM
Last modification on : Wednesday, June 8, 2022 - 12:50:05 PM


Files produced by the author(s)


  • HAL Id : hal-01939549, version 1
  • ARXIV : 1811.08725



Tatiana Shpakova, Francis Bach, Anton Osokin. Marginal Weighted Maximum Log-likelihood for Efficient Learning of Perturb-and-Map models. UAI 2018 - Conference on Uncertainty in Artificial Intelligence 2018, Aug 2018, Monterey, United States. ⟨hal-01939549⟩



Record views


Files downloads