A tutorial on variational Bayesian inference

2012

146 citations recorded by the source corpus.

Subfields: Artificial Intelligence

Citations in the corpus

• Flow Contrastive Estimation of Energy-Based Models (2019, neutral): “The gradient of the second term is similar to reverse Kullback-Leibler divergence between q α and p θ , or variational approximation of p θ by q α , which forces q α to chase the modes of p θ [52, 12].”
• A practical tutorial on autoencoders for nonlinear feature fusion: Taxonomy, models, software and guidelines (2018, neutral): “This kind of AE applies a variational Bayesian [80] approach to encoding.”
• An introduction to sampling via measure transport (2016, unknown): “Finally, setting aside the notion of nonlinear transformations, it is useful to think of the minimization problem (9) in the broader context of variational Bayesian methods [6, 40, 90, 28].”
• Structured Pruning for Deep Convolutional Neural Networks: A Survey (2023, unknown): “Variational Bayesian (VB) methods [245] are used to approximate the posterior distribution p ( θ | x ) by a variational distribution q ( θ ) .”
• VIREL: A Variational Inference Framework for Reinforcement Learning (2018, unknown): “the E-step is typically intractable, we resort to variational inference, which approximates difficult posteriors using a parameterised variational distribution q(h;) (Beal, 2003; Tzikas et al., 2008; Fox and Roberts, 2010). The objective of variational inference is therefore to reduce the KL divergen”