Black-box variational inference is widely used in situations where there is no proof that its
stochastic optimization succeeds. We suggest this is due to a theoretical gap in existing …

Black-box variational inference (BBVI) now sees widespread use in machine learning and
statistics as a fast yet flexible alternative to Markov chain Monte Carlo methods for …

Understanding the gradient variance of black-box variational inference (BBVI) is a crucial
step for establishing its convergence and develo** algorithmic improvements. However …

Data-driven methods such as reinforcement and imitation learning have achieved
remarkable success in robot autonomy. However, their data-centric nature still hinders them …

We prove that black-box variational inference (BBVI) with control variates, particularly the
sticking-the-landing (STL) estimator, converges at a geometric (traditionally called “linear”) …

In model-based reinforcement learning (MBRL), policy gradients can be estimated either by
derivative-free RL methods, such as likelihood ratio gradients (LR), or by backpropagating …

Black-box variational inference (BBVI) now sees widespread use in machine learning and
statistics as a fast yet flexible alternative to Markov chain Monte Carlo methods for …

We present a novel approach for black-box VI that bypasses the difficulties of stochastic
gradient ascent, including the task of selecting step-sizes. Our approach involves using a …

Stochastic gradient-based optimisation for discrete latent variable models is challenging due
to the high variance of gradients. We introduce a variance reduction technique for score …

Recent work in variational inference (VI) has used ideas from Monte Carlo estimation to
obtain tighter lower bounds on the log-likelihood to be used as objectives for VI. However …