Timezone: »

CO-BED: Information-Theoretic Contextual Optimization via Bayesian Experimental Design
Desi Ivanova · Joel Jennings · Tom Rainforth · Cheng Zhang · Adam Foster

Thu Jul 27 01:30 PM -- 03:00 PM (PDT) @ Exhibit Hall 1 #117

We formalize the problem of contextual optimization through the lens of Bayesian experimental design and propose CO-BED---a general, model-agnostic framework for designing contextual experiments using information-theoretic principles. After formulating a suitable information-based objective, we employ black-box variational methods to simultaneously estimate it and optimize the designs in a single stochastic gradient scheme. In addition, to accommodate discrete actions within our framework, we propose leveraging continuous relaxation schemes, which can naturally be integrated into our variational objective. As a result, CO-BED provides a general and automated solution to a wide range of contextual optimization problems. We illustrate its effectiveness in a number of experiments, where CO-BED demonstrates competitive performance even when compared to bespoke, model-specific alternatives.

Author Information

Desi Ivanova (University of Oxford)
Joel Jennings (Microsoft)
Tom Rainforth (University of Oxford)
Cheng Zhang (Microsoft Research, Cambridge)
Adam Foster (Microsoft Research)

More from the Same Authors