AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

A Framework for Improving the Reliability of Black-box Variational Inference

Manushi Welandawe, Michael Riis Andersen, Aki Vehtari, Jonathan H. Huggins

JMLR 2024 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Variational inference theory and gradients · 18 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use RABVI with termination rule instead of fixed-learning-rate and decay-schedule optimizersAdam/RMSProp/SGD/ADVI baselines · Gaussian targetssqrt symmetrized KLImproved
add automated termination rule on top of Adam with exponential decay or cosine scheduleAdam-ED, Adam-C · Gaussian targetssqrt symmetrized KLNo clear effect
use iterate averaging (avgAdam/avgRMSProp) vs other optimizers NGD and SQN inside RABVI (ablation)RABVI · Gaussian targetssymmetrized KL improvementMixed
switch from mean-field Gaussian to full-rank Gaussian family (ablation)RABVI · posteriordb (18 models)relative mean and std errorImproved
switch to real-NVP normalizing flow family (with FASO) (ablation)FASO · posteriordb (18 models)relative mean and std errorMixed
compare RABVI to dynamic HMC at equal likelihood evaluationsRABVI · posteriordb (18 models)relative mean errorMixed
vary initial learning rate, window size, thresholds tau and eps0 (ablation)RABVI · Gaussian targets, dogs, arKaccuracy and runtimeNo clear effect
use extreme tuning values (learning rate 0.01 or M at most 5 Monte Carlo samples) (ablation)RABVI · Gaussian targets, dogs, arKruntimeHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy