Fast Bundle Algorithm for Multiple-Instance Learning
- 13 October 2011
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 34 (6) , 1068-1079
Abstract
We present a bundle algorithm for multiple-instance classification and ranking. These frameworks yield improved models on many problems possessing special structure. Multiple-instance loss functions are typically nonsmooth and nonconvex, and current algorithms convert these to smooth nonconvex optimization problems that are solved iteratively. Inspired by the latest linear-time subgradient-based methods for support vector machines, we optimize the objective directly using a nonconvex bundle method. Computational results show this method is linearly scalable, while not sacrificing generalization accuracy, permitting modeling on new and larger data sets in computational chemistry and other applications. This new implementation facilitates modeling with kernels.Keywords
This publication has 27 references indexed in Scilit:
- Cytochromes P450: A Structure-Based Summary of Biotransformations Using Representative SubstratesDrug Metabolism Reviews, 2008
- Multiple Instance Classification via Successive Linear ProgrammingJournal of Optimization Theory and Applications, 2007
- Cytochrome P450 and Chemical ToxicologyChemical Research in Toxicology, 2007
- Empirical Regioselectivity Models for Human Cytochromes P450 3A4, 2D6, and 2C9Journal of Medicinal Chemistry, 2007
- Minimizing Nonconvex Nonsmooth Functions via Cutting Planes and Proximity ControlSIAM Journal on Optimization, 2004
- A Model for Predicting Likely Sites of CYP3A4-mediated Metabolism on Drug-like MoleculesJournal of Medicinal Chemistry, 2003
- Survey of Bundle Methods for Nonsmooth OptimizationOptimization Methods and Software, 2002
- RSVM: Reduced Support Vector Machines2001
- Solving the multiple instance problem with axis-parallel rectanglesArtificial Intelligence, 1997
- A method of conjugate subgradients for minimizing nondifferentiable functions1975