Emulating complex codes: The implications of using separable covariance functions

32 mins 13 secs, 29.50 MB, MP3 44100 Hz, 125.01 kbits/sec

Share this media item:

Embed this media item:

<iframe width="_width_" height="_height_" src="https://sms.cam.ac.uk/media/1171639/embed" frameborder="0" scrolling="no" allowfullscreen></iframe>

Choose size:

About this item

Available Formats

About this item

Description:	Rougier, J (University of Bristol) Monday 05 September 2011, 16:30-17:00

Created:

2011-09-13 13:07

Collection:

Design and Analysis of Experiments

Publisher:

Isaac Newton Institute

Rougier, J

Language:

eng (English)

Credits:

Author:	Rougier, J
Director:	Steve Greenham


Abstract:	Emulators are crucial in experiments where the computer code is sufficiently expensive that the ensemble of runs cannot span the parameter space. In this case they allow the ensemble to be augmented with additional judgements concerning smoothness and monotonicity. The emulator can then replace the code in inferential calculations, but in my experience a more important role for emulators is in trapping code errors. The theory of emulation is based around the construction of a stochastic processes prior, which is then updated by conditioning on the runs in the ensemble. Almost invariably, this prior contains a component with a separable covariance function. This talk considers exactly what this separability implies for the nature of the underlying function. The strong conclusion is that processes with separable covariance functions are second-order equivalent to the product of second-order uncorrelated processes. This is an alarmingly strong prior judgement about the computer code, ruling out interactions. But, like the property of stationarity, it does not survive the conditioning process. The cautionary response is to include several regression terms in the emulator prior.

Abstract:

Emulators are crucial in experiments where the computer code is sufficiently expensive that the ensemble of runs cannot span the parameter space. In this case they allow the ensemble to be augmented with additional judgements concerning smoothness and monotonicity. The emulator can then replace the code in inferential calculations, but in my experience a more important role for emulators is in trapping code errors.

The theory of emulation is based around the construction of a stochastic processes prior, which is then updated by conditioning on the runs in the ensemble. Almost invariably, this prior contains a component with a separable covariance function. This talk considers exactly what this separability implies for the nature of the underlying function. The strong conclusion is that processes with separable covariance functions are second-order equivalent to the product of second-order uncorrelated processes.

This is an alarmingly strong prior judgement about the computer code, ruling out interactions. But, like the property of stationarity, it does not survive the conditioning process. The cautionary response is to include several regression terms in the emulator prior.

Available Formats

Format	Quality	Bitrate	Size
MPEG-4 Video	640x360	1.84 Mbits/sec	449.81 MB	View	Download
WebM	640x360	1.56 Mbits/sec	379.17 MB	View	Download
Flash Video	484x272	569.03 kbits/sec	135.10 MB	View	Download
iPod Video	480x270	506.27 kbits/sec	120.26 MB	View	Download
MP3 *	44100 Hz	125.01 kbits/sec	29.50 MB	Listen	Download
Auto	(Allows browser to choose a format it supports)