Empirical Bernstein stopping

Mnih, Volodymyr and Szepesvári, Csaba and Audibert, Jean-Yves (2008) Empirical Bernstein stopping. In: ICML 2008. 25th international conference on machine learning. Helsinki, 2008. (ACM international conference proceeding series 307.).

[img] Text
bernsteinstopping.pdf - Published Version
Restricted to Registered users only

Download (264kB)


Sampling is a popular way of scaling up machine learning algorithms to large datasets. The question often is how many samples are needed. Adaptive stopping algorithms monitor the performance in an online fashion and they can stop early, saving valuable resources. We consider problems where probabilistic guarantees are desired and demonstrate how recently-introduced empirical Bernstein bounds can be used to design stopping rules that are efficient. We provide upper bounds on the sample complexity of the new rules, as well as empirical results on model selection and boosting in the filtering setting.

Item Type: Conference or Workshop Item (Paper)
Subjects: Q Science > QA Mathematics and Computer Science > QA75 Electronic computers. Computer science / számítástechnika, számítógéptudomány
Depositing User: Eszter Nagy
Date Deposited: 11 Dec 2012 15:32
Last Modified: 11 Dec 2012 15:32
URI: https://eprints.sztaki.hu/id/eprint/5600

Update Item Update Item