Variational Inference with Tail-adaptive f-Divergence

V ariational inference (VI) (e.g., Jordan et al., 1999; Wainwright et al., 2008) has been established Combined with techniques like stochastic optimization (Ranganath et al., A key component of successful variational inference lies on choosing a proper divergence metric. Work done at UT Austin 32nd Conference on Neural Information Processing Systems (NeurIPS 2018), Montréal, Canada.