#arxivfeed :

"Neural network with optimal neuron activation functions based on additive Gaussian process regression"
https://arxiv.org/abs/2301.05567

#MachineLearning #DeepLearning #GaussianProcess

#arxivfeed :

"Dynamic Bayesian Learning and Calibration of Spatiotemporal Mechanistic Systems"
https://arxiv.org/abs/2208.06528

#DynamicalSystems #ModelCalibration #Bayesian #ParameterEstimation #GaussianProcess

Take the idea of random Fourier features, as applied to #GaussianProcess regression in #MachineLearning. There is a method in the probabilistic numerics textbook about Gaussian quadrature (same Gauss, different method) which gives good convergence with respect to the spectrum of a function. Show that a high quality #kernel (low rank approximation) can be computed efficiently (sublinear in the number of training points).
https://www.jmlr.org/papers/v23/21-0030.html

Take the idea of random Fourier features, as applied to #GaussianProcess regression in #MachineLearning. There is a method in the probabilistic numerics textbook about Gaussian quadrature (same Gauss, different method) which gives good convergence with respect to the spectrum of a function. Show that a high quality #kernel (low rank approximation) can be computed efficiently (sublinear in the number of training points).
https://www.jmlr.org/papers/v23/21-0030.html

Been trying out a lot of #GaussianProcess libraries in #python lately. For what my opinion is worth, I'm really enjoying using GPFlow.

It seems to have a good balance that you can customize the things you want, and not have to over-worry about the rest. Documentation includes simple examples to very advanced. Comprehensive enough for a guy like me to get a model up and running in a couple hours on real data.

@FCAI Update on Zheyang’s status: The opponent got there on the last minute, gave an enlightening view of the position of the thesis in #BayesianModeling and #GaussianProcess es, and asked a set of broad and challenging questions. Zheyand did outstandingly well, with still some unsolved questions which he will be eager to pursue when on the job market at some point. Big congrats Zheyang Shen and many thanks opponent Chris Oates! #PhD #AaltoUniversity @FCAI

#arxivfeed :

"Towards Improved Learning in Gaussian Processes: The Best of Two Worlds"
https://arxiv.org/abs/2211.06260

#inference #GaussianProcess #ExpectationPropagation #VariationalInference #classification

#introduction
I'm a researcher in social-ecological system #modeling. I'm interested in providing decision making tools to manage systems which can be impacted by extreme events. To this end, I use non-parametric methods (like #gaussianprocess) to infer ecological dynamics and to produce viable or optimal control policies. I worked at UCSC in multi-species #fisheries management and I'm ending a postdoctoral position at UCA (France) in agro-ecological modeling.

Glad to be here on Mastodon!