Scalable Gaussian Processes for Characterizing Multidimensional Change Surfaces
نویسندگان
چکیده
We present a scalable Gaussian process model for identifying and characterizing smooth multidimensional changepoints, and automatically learning changes in expressive covariance structure. We use Random Kitchen Sink features to flexibly define a change surface in combination with expressive spectral mixture kernels to capture the complex statistical structure. Through the use of novel methods for additive nonseparable kernels, we scale the model to large datasets. We demonstrate the model on numerical simulations as well as applying it to real world spatio-temporal data. Specifically, we model state level incidence rates of measles in the United States both before and after the introduction of the measles vaccine. Additionally we model zip code level requests for lead testing kits in New York City over the past two years in the midst of heightened concerns about lead-tainted water. Email: [email protected] Email: [email protected] Email: [email protected] Email: [email protected]
منابع مشابه
GPatt: Fast Multidimensional Pattern Extrapolation with Gaussian Processes
Gaussian processes are typically used for smoothing and interpolation on small datasets. We introduce a new Bayesian nonparametric framework – GPatt – enabling automatic pattern extrapolation with Gaussian processes on large multidimensional datasets. GPatt unifies and extends highly expressive kernels and fast exact inference techniques. Without human intervention – no hand crafting of kernel ...
متن کاملFast Kernel Learning for Multidimensional Pattern Extrapolation
The ability to automatically discover patterns and perform extrapolation is an essential quality of intelligent systems. Kernel methods, such as Gaussian processes, have great potential for pattern extrapolation, since the kernel flexibly and interpretably controls the generalisation properties of these methods. However, automatically extrapolating large scale multidimensional patterns is in ge...
متن کاملThoughts on Massively Scalable Gaussian Processes
We introduce a framework and early results for massively scalable Gaussian processes (MSGP), significantly extending the KISS-GP approach of Wilson and Nickisch (2015). The MSGP framework enables the use of Gaussian processes (GPs) on billions of datapoints, without requiring distributed inference, or severe assumptions. In particular, MSGP reduces the standard O(n) complexity of GP learning an...
متن کاملThe Rate of Entropy for Gaussian Processes
In this paper, we show that in order to obtain the Tsallis entropy rate for stochastic processes, we can use the limit of conditional entropy, as it was done for the case of Shannon and Renyi entropy rates. Using that we can obtain Tsallis entropy rate for stationary Gaussian processes. Finally, we derive the relation between Renyi, Shannon and Tsallis entropy rates for stationary Gaussian proc...
متن کاملCovariance Kernels for Fast Automatic Pattern Discovery and Extrapolation with Gaussian Processes
Truly intelligent systems are capable of pattern discovery and extrapolation without human intervention. Bayesian nonparametric models, which can uniquely represent expressive prior information and detailed inductive biases, provide a distinct opportunity to develop intelligent systems, with applications in essentially any learning and prediction task. Gaussian processes are rich distributions ...
متن کامل