University of Cambridge > > Machine Learning @ CUED > Bayesian optimisation in many dimensions with bespoke probabilistic programs

Bayesian optimisation in many dimensions with bespoke probabilistic programs

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact .

In this talk, I will present a collection of techniques to make Bayesian optimisation converge in grey-box optimisation problems with many dimensions. First, I will discuss how better priors of the objective function can lead to orders of magnitude improvements in convergence. I will use probabilistic programming to build probabilistic models that have good convergence and can leverage many observable properties of the objective function for inference. I will introduce a class of probabilistic programs that are both useful for Bayesian optimisation and support inference at a reasonable computational cost. Second, I will discuss techniques to help the numerical optimisation stage of the Bayesian optimisation converge, when algorithms such as DIRECT or CMA -ES are not sufficient.

I will present applications of these techniques to optimise the configuration of computer systems, such as TensorFlow, and maximise their computational performance. The techniques will be exemplified using the BOAT framework (a framework to build BespOke Auto-Tuners) which is open source and available at

This talk is part of the Machine Learning @ CUED series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.


© 2006-2023, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity