Black-Box Alpha Divergence Minimization

By José Miguel Hernández-Lobato, Yingzhen Li, Mark Rowland, Thang D. Bui, Daniel Hernández-Lobato, Richard E. Turner. 2016

61 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Deep Bayesian Bandits Showdown: An Empirical Comparison of Bayesian Deep Networks for Thompson Sampling (2018, methodology): “In particular, in 4 Published as a conference paper at ICLR 2018 this work, we implement the black-box α-divergence minimization algorithm (Hernández-Lobato et al., 2016), where local parameter sharing is applied to the Power EP energy function.”
Distributed Bayesian Learning with Stochastic Natural Gradient Expectation Propagation and the Posterior Server (2015, methodology): “C samplers targeting the tilted distributions. Black-box methods have recently been developed for variational Bayes (Ranganath et al., 2014, Black-box Variational Inference or BBVI) and for power EP (Hernandez-Lobato et al., 2016, Black-box Alpha or BB- ). BB- and SNEP are both methods for Bayesian ”
Advances in Variational Inference (2017, methodology): “[6]. Both the KL divergence and the Hellinger distance are special cases of a-divergence. Different formulations of the a-divergence exist [6], [200], and various VI methods use different definitions [95], [114]. We focus on Renyi’s formulation, which is deﬁned as: DR a(pjjq)= 1 a 1 log Z p(x)aq(x)1”
Uncertainty in Deep Learning (2016, methodology): “Closely related to PBP are the recently suggested approximate inference techniques based on α-divergence minimisation [Hernández-Lobato et al., 2016; Li and Turner, 2016; Minka, 2005].”
A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges (2020, methodology): “[370] introduced a novel approximate inference method based on the”
A survey of uncertainty in deep neural networks (2021, background): “Some examples are (i) approximate inference techniques such as alpha divergence [124], [125], [126], expectation propagation [127], [128], assumed density”