jamesrobertlloyd / gp-structure-search

MIT License
229 stars 83 forks source link

Inference fail loop #2

Open jamesrobertlloyd opened 11 years ago

jamesrobertlloyd commented 11 years ago

If any code fails (e.g. ill conditioned covariance matrix) the experiment can get stuck in an infinite loop

I observed this in the prediction code once - quick fix was to change the starting noise parameter very slightly.

jamesrobertlloyd commented 11 years ago

Noticed it again - need to be wary of this.