Online temporally adaptive parameter estimation with applications to streaming data analysis.

Add to your list(s) Download to your calendar using vCal

• Cristoforos Anagnostopoulos, Statistics Laboratory, University of Cambridge
• Wednesday 03 November 2010, 14:15-15:00
• LR10, Engineering, Department of.

If you have a question about this talk, please contact Rachel Fogg.

Online learning algorithms deployed in streaming data contexts may be additionally required to possess temporally adaptive properties, in order to remain up-to-date against unforeseen changes, smooth or abrupt, in the underlying data generation mechanism. In cases where explicit dynamic modelling is either impossible or impractical, temporally adaptive behaviour may still be induced by controlling the responsiveness of the estimator to novel information. This can be naturally accomplished in certain algorithms that feature user-specified learning rates, such as the Robbins-Monro family of algorithms. We discuss available methodology for automatic self-tuning learning rates in a Robbins-Monro context. On the basis of both theoretical insights and real-data experiments, we demonstrate that this approach can efficiently handle temporal variation of unknown characteristics, while additionally serving as a monitoring tool.

This talk is part of the Signal Processing and Communications Lab Seminars series.

This talk is included in these lists:

• All Talks (aka the CURE list)
• Cambridge Centre for Data-Driven Discovery (C2D3)
• Cambridge University Engineering Department Talks
• Cambridge talks
• Centre for Smart Infrastructure & Construction
• Chris Davis' list
• Computational Continuum Mechanics Group Seminars
• Featured lists
• Information Engineering Division seminar list
• Interested Talks
• LR10, Engineering, Department of
• School of Technology
• Signal Processing and Communications Lab Seminars
• Trust & Technology Initiative - interesting events
• bld31
• ndk22's list
• ob366-ai4er
• rp587

Note that ex-directory lists are not shown.