Solving multiclass support vector machines with LaRank
- 20 June 2007
- conference paper
- Published by Association for Computing Machinery (ACM)
Abstract
International audienceOptimization algorithms for large margin multiclass recognizers are often too costly to handle ambitious problems with structured outputs and exponential numbers of classes. Optimization algorithms that rely on the full gradient are not effective because, unlike the solution, the gradient is not sparse and is very large. The LaRank algorithm sidesteps this difficulty by relying on a randomized exploration inspired by the perceptron algorithm. We show that this approach is competitive with gradient based optimizers on simple multiclass ..Keywords
This publication has 7 references indexed in Scilit:
- Predicting Structured DataPublished by MIT Press ,2007
- The Huller: A Simple and Efficient Online SVMPublished by Springer Nature ,2005
- Learning structured prediction modelsPublished by Association for Computing Machinery (ACM) ,2005
- A comparison of methods for multiclass support vector machinesIEEE Transactions on Neural Networks, 2002
- Discriminative training methods for hidden Markov modelsPublished by Association for Computational Linguistics (ACL) ,2002
- 10.1162/jmlr.2003.3.4-5.951Applied Physics Letters, 2000
- A quadratic programming procedureNaval Research Logistics Quarterly, 1957