Multiple Kernel Multivariate Performance Learning Using Cutting Plane Algorithm
Authors:
- 1 October 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1870-1875
Abstract
In this paper, we propose a multi-kernel classifier learning algorithm to optimize a given nonlinear and nonsmoonth multivariate classifier performance measure. Moreover, to solve the problem of kernel function selection and kernel parameter tuning, we proposed to construct an optimal kernel by weighted linear combination of some candidate kernels. The learning of the classifier parameter and the kernel weight are unified in a single objective function considering to minimize the upper boundary of the given multivariate performance measure. The objective function is optimized with regard to classifier parameter and kernel weight alternately in an iterative algorithm by using cutting plane algorithm. The developed algorithm is evaluated on two different pattern classification methods with regard to various multivariate performance measure optimization problems. The experiment results show the proposed algorithm outperforms the competing methods.Keywords
All Related Versions
This publication has 43 references indexed in Scilit:
- Towards Scalable Distributed Workload Manager with Monitoring-Based Weakly Consistent Resource Stealing2015
- Optimizing load balancing and data-locality with data-aware scheduling2014
- FusionFS: Toward supporting data-intensive scientific applications on extreme-scale high-performance computing systems2014
- Sparse matrix-vector multiply on the Keystone II Digital Signal Processor2014
- Next generation job management systems for extreme-scale ensemble computing2014
- A Multi-Agent-Based Intelligent Sensor and Actuator Network Design for Smart House and Home AutomationJournal of Sensor and Actuator Networks, 2013
- ZHT: A Light-Weight Reliable Persistent Dynamic Scalable Zero-Hop Distributed Hash Table2013
- Accelerating frequent itemset mining on graphics processing unitsThe Journal of Supercomputing, 2013
- Investigations on the physical limitation and electrostatic improvement of a gate-all-around silicon nanowire transistor with Schottky barrier source/drainSemiconductor Science and Technology, 2009
- Experimental investigations on channel backscattering characteristics of gate-all-around silicon nanowire transistors from top-down approachApplied Physics Letters, 2008