A Variational Inference-Based Heteroscedastic Gaussian Process Approach for Simulation Metamodeling

2019 ◽  
Vol 29 (1) ◽  
pp. 1-22 ◽  
Author(s):  
Wenjing Wang ◽  
Nan Chen ◽  
Xi Chen ◽  
Linchang Yang
Keyword(s):  
Gaussian Process ◽  
Process Approach ◽  
Variational Inference ◽  
Simulation Metamodeling

Gaussian process approach for metric learning

2019 ◽  
Vol 87 ◽  
pp. 17-28 ◽  
Author(s):  
Ping Li ◽  
Songcan Chen
Keyword(s):  
Gaussian Process ◽  
Metric Learning ◽  
Process Approach

Gaussian Process Approach to Buried Object Size Estimation in GPR Images

2010 ◽  
Vol 7 (1) ◽  
pp. 141-145 ◽  
Author(s):  
Edoardo Pasolli ◽  
Farid Melgani ◽  
Massimo Donelli
Keyword(s):  
Gaussian Process ◽  
Process Approach ◽  
Object Size ◽  
Size Estimation ◽  
Buried Object

scholarly journals Variational Inference for Sparse Gaussian Process Modulated Hawkes Process

2020 ◽  
Vol 34 (04) ◽  
pp. 6803-6810
Author(s):  
Rui Zhang ◽  
Christian Walder ◽  
Marian-Andrei Rizoiu
Keyword(s):  
Model Selection ◽  
Gaussian Process ◽  
Linear Time ◽  
Expectation Maximization Algorithm ◽  
Synthetic Data ◽  
Variational Inference ◽  
Hawkes Process ◽  
Prediction Confidence ◽  
Inference Schema ◽  
Non Parametric

The Hawkes process (HP) has been widely applied to modeling self-exciting events including neuron spikes, earthquakes and tweets. To avoid designing parametric triggering kernel and to be able to quantify the prediction confidence, the non-parametric Bayesian HP has been proposed. However, the inference of such models suffers from unscalability or slow convergence. In this paper, we aim to solve both problems. Specifically, first, we propose a new non-parametric Bayesian HP in which the triggering kernel is modeled as a squared sparse Gaussian process. Then, we propose a novel variational inference schema for model optimization. We employ the branching structure of the HP so that maximization of evidence lower bound (ELBO) is tractable by the expectation-maximization algorithm. We propose a tighter ELBO which improves the fitting performance. Further, we accelerate the novel variational inference schema to linear time complexity by leveraging the stationarity of the triggering kernel. Different from prior acceleration methods, ours enjoys higher efficiency. Finally, we exploit synthetic data and two large social media datasets to evaluate our method. We show that our approach outperforms state-of-the-art non-parametric frequentist and Bayesian methods. We validate the efficiency of our accelerated variational inference schema and practical utility of our tighter ELBO for model selection. We observe that the tighter ELBO exceeds the common one in model selection.

A multi-objective Gaussian process approach for optimization and prediction of carbonization process in carbon fiber production under uncertainty

2019 ◽  
Vol 2 (3) ◽  
pp. 444-455 ◽  
Author(s):  
Milad Ramezankhani ◽  
Bryn Crawford ◽  
Hamid Khayyam ◽  
Minoo Naebe ◽  
Rudolf Seethaler ◽  
...  
Keyword(s):  
Carbon Fiber ◽  
Gaussian Process ◽  
Process Approach ◽  
Fiber Production ◽  
Carbonization Process ◽  
Multi Objective
Sign in / Sign up

Export Citation Format

Share Document