Finito: A faster, permutable incremental gradient method for big data problems

31st International Conference on Machine Learning, ICML 2014

Volumn 4, Issue , 2014, Pages 2839-2855

  Defazio, Aaron J ^a   Caetano, Tibério S ^a   Domke, Justin ^a  

^a AUSTRALIAN NATIONAL UNIVERSITY   (Australia)

Author keywords

[No Author keywords available]

Indexed keywords

ARTIFICIAL INTELLIGENCE; GRADIENT METHODS; LEARNING SYSTEMS; OPTIMIZATION; SITE SELECTION;

BLACK BOXES; CONVERGENCE RATES; DATA PROBLEMS; FINITE SUMS; OPTIMIZATION THEORY; SAMPLING WITHOUT REPLACEMENTS; STATE-OF-THE-ART PERFORMANCE;

BIG DATA;

EID: 84919829570     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (11)

1. Bertsekas, Dimitri P. Incremental gradient, subgradient, and proximal methods for convex optimization: A survey. Technical report, 2010.
2. Mairal, Julien. Optimization with first-order surrogate functions. ICML, 2013.
3. Mairal, Julien. Incremental majorization-minimization optimization with application to large-scale machine learning. Technical report, INRIA Grenoble Rhne-Alpes/LJK Laboratoire Jean Kuntzmann, 2014.
4. Nedic, Angelia and Bertsekas, Dimitri. Stochastic Optimization: Algorithms and Applications, chapter Convergence Rate of Incremental Subgradient Algorithms. Kluwer Academic, 2000.
5. Nesterov, Yu. On an approach to the construction of optimal methods of minimization of smooth convex functions. Ekonomika i Mateaticheskie Metody, 24:509-517, 1988.
6. Nesterov, Yu. Introductory Lectures On Convex Programming. Springer, 1998.
7. Nesterov, Yu. Efficiency of coordinate descent methods on huge-scale optimization problems. Technical report, CORE, 2010.
8. Recht, Benjamin and Re, Christopher. Beneath the valley of the noncommutative arithmetic-geometric mean inequality: conjectures, case-studies, and consequences. Technical report, University of Wisconsin-Madison, 2012.
9. Richtarik, Peter and Takac, Martin. Iteration complexity of randomized block-coordinate descent methods for minimizing a composite function. Technical report, University of Edinburgh, 2011.
10. Schmidt, Mark, Roux, Nicolas Le, and Bach, Francis. Minimizing finite sums with the stochastic average gradient. Technical report, INRIA, 2013.
11. Shalev-Shwartz, Shai and Zhang, Tong. Stochastic dual coordinate ascent methods for regularized loss minimization. JMLR, 2013.