An Automatic Approximate Bayesian Computation Approach Using Metric Learning
Recent progress in Bayesian inference has allowed for accurate posterior estimations in complex situations with no idea about a likelihood function. Currently, Approximate Bayesian Computation (ABC) techniques have emerged as a widely used set of free-likelihood methods. Although there is a large number of different ABC-based approaches across the literature, all they have in common a hard dependence on free parameters selection, demanding for expensive tuning procedures such as grid search or cross-validation. Here, we introduce an Automatic Metric Learning-based ABC approach, termed AML-ABC. Namely, AML-ABC matches the simulation and observation spaces within an ABC-based framework. Attained results on a synthetic dataset and a real-world ecological system show that our approach is a competitive method compared to other non-automatic state-of-the-art ABC techniques.
KeywordsApproximate Bayesian Computation Kernel methods Metric learning Non-linear dynamic system Statistical inference
Research under grants provided by the project 1110-745-58696, funded by Colciencias, Colombia. Authors would like to thank the Master in Electrical Engineering program from Universidad Tecnológica de Pereira for partially funding this research. Moreover, author W. González-Vanegas was supported under the project E6-18-2, funded by Universidad Tecnológica de Pereira.
- 4.González-Vanegas, W., Alvarez-Meza, A., Orozco-Gutierrez, Á.: Sparse hilbert embedding-based statistical inference of stochastic ecological systems. In: Mendoza, M., Velastín, S. (eds.) CIARP 2017. LNCS, vol. 10657, pp. 255–262. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-75193-1_31CrossRefGoogle Scholar
- 6.Meeds, E., Welling, M.: GPS-ABC: Gaussian process surrogate approximate Bayesian computation. arXiv preprint arXiv:1401.2838 (2014)
- 7.Mitrovic, J., Sejdinovic, D., Teh, Y.W.: DR-ABC: approximate Bayesian computation with kernel-based distribution regression. In: International Conference on Machine Learning, ICML 2016, vol. 48, pp. 1482–1491 (2016)Google Scholar
- 9.Park, M., Jitkrittum, W., Sejdinovic, D.: K2-ABC: approximate Bayesian computation with kernel embeddings. arXiv preprint arXiv:1502.02558 (2015)
- 11.Pigorsch, E.G.C.: Approximate Bayesian computation with indirect summary statistics. Technical report (2013)Google Scholar