Inference from complex distributions is a common problem in machine learning needed for many Bayesian methods. We propose an efficient, gradient-free method for learning general GMM approximations of multimodal distributions based on recent insights from stochastic search methods. Our method establishes information-geometric trust regions to ensure efficient exploration of the sampling space and stability of the GMM updates, allowing for efficient estimation of multi-variate Gaussian variational distributions. For GMMs, we apply a variational lower bound to decompose the learning objective into sub-problems given by learning the individual mixture components and the coefficients. The number of mixture components is adapted online in order to allow for arbitrary exact approximations. We demonstrate on several domains that we can learn significantly better approximations than competing variational inference methods and that the quality of samples drawn from our approximations is on par with samples created by state-of-the-art MCMC samplers that require significantly more computational resources.
|Title of host publication||Proceedings of the 35th International Conference on Machine Learning|
|Editors||Jennifer Dy, Andreas Krause|
|Number of pages||10|
|Publication status||Published - 1 Jul 2018|
|Event||35th International Conference on Machine Learning, ICML 2018 - Stockholm, Sweden|
Duration: 10 Jul 2018 → 15 Jul 2018
|Name||Proceedings of Machine Learning Research|
|Conference||35th International Conference on Machine Learning, ICML 2018|
|Period||10/07/18 → 15/07/18|
FingerprintDive into the research topics of 'Efficient Gradient-Free Variational Inference using Policy Search'. Together they form a unique fingerprint.
- School of Natural & Computing Sciences, Computing Science - Lecturer
- Machine Learning
- Centre for Energy Transition