3 citations · 5 across the 5 of their papers we have counts for
Showing cs.LGShow all
3 papers · 1 filter
cs.LG2023★ 2 cited
On the Convergence of Black-Box Variational Inference
Kyurae Kim, Jisu Oh, Kaiwen Wu +2
We provide the first convergence guarantee for full black-box variational inference (BBVI), also known as Monte Carlo variational inference. While preliminary investigations worked…
cs.LG2023
Practical and Matching Gradient Variance Bounds for Black-Box Variational Bayesian Inference
Kyurae Kim, Kaiwen Wu, Jisu Oh +1
Understanding the gradient variance of black-box variational inference (BBVI) is a crucial step for establishing its convergence and developing algorithmic improvements. However, e…
cs.LG2022★ 3 cited
Markov Chain Score Ascent: A Unifying Framework of Variational Inference with Markovian Gradients
Kyurae Kim, Jisu Oh, Jacob R. Gardner +2
Minimizing the inclusive Kullback-Leibler (KL) divergence with stochastic gradient descent (SGD) is challenging since its gradient is defined as an integral over the posterior. Rec…