Kernel Implicit Variational Inference

By Jiaxin Shi, Jun Zhu. 2017

59 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

A Spectral Approach to Gradient Estimation for Implicit Distributions (2018, methodology): “This is probably due to that implicit posteriors are less likely to overfit (Shi et al., 2018), and SSGE gives accurate gradients for optimizing them.”
Eigenvalue Corrected Noisy Natural Gradient (2018, unknown): “Several non-Gaussian variational posteriors have also been proposed such as Multiplicative Normalizing Flows [Louizos and Welling, 2017] and implicit distributions [Shi et al., 2018].”
Functional Variational Bayesian Neural Networks (2019, background): “[28] Jiaxin Shi, Shengyang Sun, and Jun Zhu.”
Doubly Semi-Implicit Variational Inference (2018, methodology): “Then the marginal approximate posterior qφ(w) = ∫ qφ(w,α) dα is used to approximate the pre- dictive distribution on unseen data p(t |x,Xtr, Ttr): p(t |x,Xtr, Ttr) = ∫ p(t |x,w)p(w |Xtr, Ttr) dw = = ∫ p(t |x,w) ∫ p(w,α |Xtr, Ttr) dα dw ≈ ≈ ∫ p(t |x,w) ∫ qφ(w,α)dα dw = = ∫ p(t |x,w)qφ(w) dw. (25) The”
Semi-Implicit Variational Inference (2018, background): “…the variational family that Q belongs to, there has been signiﬁcant recent interest in deﬁning Q with an implicit model, which makes the PDF of Q become intractable (Husz´ar, 2017; Mohamed & Lakshminarayanan, 2016; Tran et al., 2017; Li & Turner, 2017; Mescheder et al., 2017; Shi et al., 2017).”
Importance Weighted Hierarchical Variational Inference (2019, methodology): “Methods based on estimates (Mescheder et al., 2017; Shi et al., 2017; Tran et al., 2017), for example, via the Density Ratio Estimation trick (Goodfellow et al., 2014; Uehara et al., 2016; Mohamed and Lakshminarayanan, 2016), typically estimate the densities indirectly utilizing an auxiliary critic…”