- 期刊
Towards Faster Model Selection in Gibbs-Sampling-Based Bayesian Classification: Discrete Gradient Approach versus Component-Wise Optimization
並列摘要
In Gibbs-sampling-based Bayesian classification, for each 'model' --i.e., for each combination of the number of clusters, degree of the corresponding polynomials, etc. --we find the posterior distribution corresponding to this model, and then we select the model with the largest marginal likelihood. For a small number of parameters, each of which has a few possible values, we can use exhaustive search to select the model. However, for a larger number of parameters, exhaustive search requires too long a computation time. So, faster model selection is needed. In this paper, we describe two possible methods for model selection: component-wise optimization and gradient ascent. We show that gradient ascent leads to faster model selection.
延伸閱讀
- Ku, C. C. (2014). Using Dynamic Bayesian Networks for Agent-Based Modelling: Application in Tuberculosis Control [master's thesis, National Taiwan University]. Airiti Library. https://doi.org/10.6342/NTU.2014.02088
- Shang, J. F. (2011). A Bayesian Multiple Comparison Procedure for Simple Order-Restricted Mixed Models with Missing Values. Journal of Data Science, 9(3), 311-330. https://doi.org/10.6339/JDS.2011.09(3).931
- Liu, Y., Zhou, K., & Lei, Y. (2015). Using Bayesian Inference Framework towards Identifying Gas Species and Concentration from High Temperature Resistive Sensor Array Data. Journal of Sensors, 2015(), 513-522-050. https://doi.org/10.1155/2015/351940
- Huang, W. Y. (2019). A Study of Bayesian Optimization and HYPERBAND for Hyperparameter Optimization [master's thesis, National Taiwan University]. Airiti Library. https://doi.org/10.6342/NTU201902022
- Kuzhali, J. V., & Vengataasalam, S. (2014). A Novel Ensemble Classifier based Classification on Large Datasets with Hybrid Feature Selection Approach. Research Journal of Applied Sciences, Engineering and Technology, 7(17), 3633-3642. https://www.airitilibrary.com/Article/Detail?DocID=20407467-201405-201507070018-201507070018-3633-3642