Skip to yearly menu bar Skip to main content


The Forget-me-not Process

Kieran Milan · Joel Veness · James Kirkpatrick · Michael Bowling · Anna Koop · Demis Hassabis

Area 5+6+7+8 #28

Keywords: [ Time Series Analysis ] [ Multi-task and Transfer Learning ] [ Bayesian Nonparametrics ] [ (Other) Probabilistic Models and Methods ] [ Online Learning ] [ Information Theory ]


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