Decomposition Methods for Differentiable Optimization Problems over Cartesian Product Sets

By Michael Patriksson. 1998

Subfields: Optimization & Training

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Optimization & Training

1. Simon Lacoste-Julien
2. Martin Jaggi
3. Peter Richtárik
4. Sebastian U. Stich
5. Mark W. Schmidt
6. Francis R. Bach
7. Jakub Konecný
8. Elad Hazan

Citations in the corpus

• Block-Coordinate Frank-Wolfe Optimization for Structural SVMs (2012, methodology): “For product domains, such a cyclic analogue of our Algorithm C.2 has already been proposed in Patriksson (1998), using a generalization of Frank-Wolfe iterations under the name ‘cost approximation’.”
• A distributed block coordinate descent method for training $l_1$ regularized linear classifiers (2014, methodology): “WEBSPAM has a much smaller number of examples and hence communication costs are low for this dataset.”
• A Functional Approximation Based Distributed Learning Algorithm (2013, methodology): “Several feature decomposition based approaches [21, 20] have been proposed in the literature.”