Improved algorithms for variational inference

Music City Center 

As an optimization-based alternative to traditional Markov chain Monte Carlo approaches, variational inference (VI) is becoming increasingly popular for approximating intractable posterior distributions in large-scale Bayesian models due to its comparable efficacy and superior computational efficiency. Several recent works provide theoretical justifications of VI by proving its statistical optimality for parameter estimation under various settings. More recently, there is increasing interest in studying algorithmic properties of popular variational inference algorithms. In this talk, we present careful modifications to Gaussian VI and coordinate ascent VI algorithms, and demonstrate their improved convergence behavior across a variety of statistical applications.