A discussion on parallelization schemes for stochastic vector quantization algorithms

ESANN 2012 proceedings, 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning

Volumn , Issue , 2012, Pages 477-482

  Durut, Matthieu ^a,c   Patra, Benoit ^b,c   Rossi, Fabrice ^d  

^a TELECOM PARISTECH   (France)

^b SORBONNE UNIVERSITÉ   (France)

^c Lokad   (France)

^d UNIVERSITÉ PARIS 1 PANTHÉON SORBONNE   (France)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMS; ARTIFICIAL INTELLIGENCE; LEARNING SYSTEMS; NETWORK ARCHITECTURE; NEURAL NETWORKS; STOCHASTIC SYSTEMS; WINDOWS OPERATING SYSTEM;

DISTRIBUTED ARCHITECTURE; DISTRIBUTED RESOURCES; DISTRIBUTED SCHEMES; MICROSOFT WINDOWS; PARALLELIZATIONS; SEQUENTIAL ALGORITHM; STOCHASTIC VECTORS; VIRTUAL MACHINES;

VECTOR QUANTIZATION;

EID: 84947773160     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (4)

1. Benoît Patra. Convergence of distributed asynchronous learning vector quantization algorithms. Journal of Machine Learning Research 12 (2011), pages 3431-3466, 2011.
2. Gilles Pagès. A space vector quantization for numerical integration. Journal of Applied and Computational Mathematics, 89:1-38, 1997.
3. Ofer Dekel, Ran Gilad-Bachrach, Ohad Shamir, and Lin Xiao. Optimal distributed online prediction using mini-batches. CoRR, abs/1012.1367, 2010.
4. Martin Zinkevich, Alex Smola, and John Langford. Slow learners are fast. In Advances in Neural Information Processing Systems 22, pages 2331-2339. 2009.