Revisiting Unbiased Implicit Variational Inference
This addresses computational bottlenecks in variational inference for machine learning practitioners, though it is incremental as it refines an existing method.
The paper tackled the computational inefficiency of unbiased implicit variational inference (UIVI) by replacing its inner MCMC loop with importance sampling and learning the optimal proposal distribution via minimizing an expected forward Kullback-Leibler divergence, achieving superior or parity performance with state-of-the-art methods on SIVI benchmarks.
Recent years have witnessed growing interest in semi-implicit variational inference (SIVI) methods due to their ability to rapidly generate samples from complex distributions. However, since the likelihood of these samples is non-trivial to estimate in high dimensions, current research focuses on finding effective SIVI training routines. Although unbiased implicit variational inference (UIVI) has largely been dismissed as imprecise and computationally prohibitive because of its inner MCMC loop, we revisit this method and show that UIVI's MCMC loop can be effectively replaced via importance sampling and the optimal proposal distribution can be learned stably by minimizing an expected forward Kullback-Leibler divergence without bias. Our refined approach demonstrates superior performance or parity with state-of-the-art methods on established SIVI benchmarks.