Sparseness vs estimating conditional probabilities : some asymptotic results
Bartlett, Peter L. & Tewari, Ambuj (2007) Sparseness vs estimating conditional probabilities : some asymptotic results. Journal of Machine Learning Research, 8(April), pp. 775-790.
One of the nice properties of kernel classifiers such as SVMs is that they often produce sparse solutions. However, the decision functions of these classifiers cannot always be used to estimate the conditional probability of the class label. We investigate the relationship between these two properties and show that these are intimately related: sparseness does not occur when the conditional probabilities can be unambiguously estimated. We consider a family of convex loss functions and derive sharp asymptotic results for the fraction of data that becomes support vectors. This enables us to characterize the exact trade-off between sparseness and the ability to estimate conditional probabilities for these loss functions.
Impact and interest:
Citation counts are sourced monthly from and citation databases.
Citations counts from theindexing service can be viewed at the linked Google Scholar™ search.
|Item Type:||Journal Article|
|Additional Information:||Fulltext freely available see link above|
|Keywords:||kernel methods, estimating conditional probabilities, sparseness, support vector machines, OAVJ|
|Subjects:||Australian and New Zealand Standard Research Classification > INFORMATION AND COMPUTING SCIENCES (080000) > ARTIFICIAL INTELLIGENCE AND IMAGE PROCESSING (080100)
Australian and New Zealand Standard Research Classification > PSYCHOLOGY AND COGNITIVE SCIENCES (170000) > COGNITIVE SCIENCE (170200)
|Divisions:||Past > QUT Faculties & Divisions > Faculty of Science and Technology
Past > Schools > Mathematical Sciences
|Copyright Owner:||Copyright 2007 Journal of Machine Learning Research|
|Deposited On:||17 Aug 2011 21:45|
|Last Modified:||29 Feb 2012 14:34|
Repository Staff Only: item control page