Poster
The Forget-me-not Process
Kieran Milan · Joel Veness · James Kirkpatrick · Michael Bowling · Anna Koop · Demis Hassabis
Area 5+6+7+8 #28
Keywords: [ Information Theory ] [ Online Learning ] [ (Other) Probabilistic Models and Methods ] [ Bayesian Nonparametrics ] [ Multi-task and Transfer Learning ] [ Time Series Analysis ]
We introduce the Forget-me-not Process, an efficient, non-parametric meta-algorithm for online probabilistic sequence prediction for piecewise stationary, repeating sources. Our method works by taking a Bayesian approach to partition a stream of data into postulated task-specific segments, while simultaneously building a model for each task. We provide regret guarantees with respect to piecewise stationary data sources under the logarithmic loss, and validate the method empirically across a range of sequence prediction and task identification problems.
Live content is unavailable. Log in and register to view live content