On the data consumption benefits of accepting increased uncertainty
Martin, Eric, Sharma, Arun, & Stephan, Frank (2004) On the data consumption benefits of accepting increased uncertainty. In Ben-David, Shai, Case, John, & Maruoka, Akira (Eds.) Algorithmic Learning Theory : proceedings of the 15th International Conference, ALT 2004, Springer-Verlag, Padova, Italy, pp. 83-98.
In the context of learning paradigms of identification in the limit, we address the question: why is uncertainty sometimes desirable? We use mind change bounds on the output hypotheses as a measure of uncertainty, and interpret ‘desirable’ as reduction in data memorization, also defined in terms of mind change bounds. The resulting model is closely related to iterative learning with bounded mind change complexity, but the dual use of mind change bounds — for hypotheses and for data — is a key distinctive feature of our approach. We show that situations exists where the more mind changes the learner is willing to accept, the lesser the amount of data it needs to remember in order to converge to the correct hypothesis. We also investigate relationships between our model and learning from good examples, set-driven, monotonic and strong-monotonic learners, as well as class-comprising versus class-preserving learnability.
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:||Conference Paper|
|Keywords:||Mind changes, long term memory, iterative learning, frugal learning|
|Subjects:||Australian and New Zealand Standard Research Classification > INFORMATION AND COMPUTING SCIENCES (080000) > COMPUTATION THEORY AND MATHEMATICS (080200)|
|Divisions:||Current > QUT Faculties and Divisions > Division of Research and Commercialisation|
|Deposited On:||27 Sep 2010 00:24|
|Last Modified:||10 Aug 2011 17:37|
Repository Staff Only: item control page