The paper proposes VIS, a variational guide that embeds several iterations of SGLD or SGD and auto-tunes the step size, claiming tighter ELBOs and faster mixing, with experiments on VAEs and state-space models.
Mcmc using hamiltonian dynamics
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Variationally Inferred Sampling Through a Refined Bound for Probabilistic Programs
The paper proposes VIS, a variational guide that embeds several iterations of SGLD or SGD and auto-tunes the step size, claiming tighter ELBOs and faster mixing, with experiments on VAEs and state-space models.