`

Timezone: »

 
Poster
Doubly Robust Bayesian Inference for Non-Stationary Streaming Data with $\beta$-Divergences
Jeremias Knoblauch · Jack E Jewson · Theodoros Damoulas

Tue Dec 04 02:00 PM -- 04:00 PM (PST) @ Room 517 AB #118
in Tue Poster Session B »
We present the very first robust Bayesian Online Changepoint Detection algorithm through General Bayesian Inference (GBI) with $\beta$-divergences. The resulting inference procedure is doubly robust for both the predictive and the changepoint (CP) posterior, with linear time and constant space complexity. We provide a construction for exponential models and demonstrate it on the Bayesian Linear Regression model. In so doing, we make two additional contributions: Firstly, we make GBI scalable using Structural Variational approximations that are exact as $\beta \to 0$. Secondly, we give a principled way of choosing the divergence parameter $\beta$ by minimizing expected predictive loss on-line. Reducing False Discovery Rates of \CPs from up to 99\% to 0\% on real world data, this offers the state of the art.
Keywords: Online Learning · Variational Inference · Time Series Analysis · Bayesian Theory

Author Information

Jeremias Knoblauch (Warwick University)
Jack E Jewson (University of Warwick)
Theodoros Damoulas (University of Warwick The Alan Turing Institute)

More from the Same Authors