McHutchon, A and Rasmussen, CE (2011) Gaussian Process training with input noise. Advances in Neural Information Processing Systems 24: 25th Annual Conference on Neural Information Processing Systems 2011, NIPS 2011.Full text not available from this repository.
In standard Gaussian Process regression input locations are assumed to be noise free. We present a simple yet effective GP model for training on input points corrupted by i.i.d. Gaussian noise. To make computations tractable we use a local linear expansion about each input point. This allows the input noise to be recast as output noise proportional to the squared gradient of the GP posterior mean. The input noise variances are inferred from the data as extra hyperparameters. They are trained alongside other hyperparameters by the usual method of maximisation of the marginal likelihood. Training uses an iterative scheme, which alternates between optimising the hyperparameters and calculating the posterior gradient. Analytic predictive moments can then be found for Gaussian distributed test points. We compare our model to others over a range of different regression problems and show that it improves over current methods.
|Divisions:||Div F > Computational and Biological Learning|
|Depositing User:||Unnamed user with email firstname.lastname@example.org|
|Date Deposited:||18 May 2016 19:19|
|Last Modified:||24 Aug 2016 01:55|