Rademacher and Gaussian complexities: Risk bounds and structural results
Bartlett, P. L. & Mendelson, S. (2003) Rademacher and Gaussian complexities: Risk bounds and structural results. Journal of Machine Learning Research, 3(3), pp. 463-482.
We investigate the use of certain data-dependent estimates of the complexity of a function class, called Rademacher and Gaussian complexities. In a decision theoretic setting, we prove general risk bounds in terms of these complexities. We consider function classes that can be expressed as combinations of functions from basis classes and show how the Rademacher and Gaussian complexities of such a function class can be bounded in terms of the complexity of the basis classes. We give examples of the application of these techniques in finding data-dependent risk bounds for decision trees, neural networks and support vector machines.
Impact and interest:
Citation countsare sourced monthly fromand citation databases.
Citations counts from theindexing service can be viewed at the linked Google Scholar™ search.
|Item Type:||Journal Article|
|Keywords:||Data-Dependent Complexity, Error Bounds, Maximum Discrepancy, Rademacher Averages, Data reduction, Error analysis, Neural networks, Gaussian complexities, Learning systems, 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
|Deposited On:||12 Aug 2011 13:17|
|Last Modified:||12 Aug 2011 13:17|
Repository Staff Only: item control page