The Forget-me-not Process

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.

Authors

• Kieran Milan Google DeepMind
• Joel Veness
• James Kirkpatrick Google DeepMind
• Michael Bowling University of Alberta
• Anna Koop Google DeepMind
• Demis Hassabis

Keywords

No keywords are indexed for this paper.