AI Paper Atlas

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

Hierarchical Importance Weighted Autoencoders

Chin-Wei Huang, Kris Sankaran, Eeshan Dhekane, Alexandre Lacoste, Aaron Courville

ICML 2019 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Amortized and online variational inference · 5 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 H-IWAE with α=1 instead of IWAE at K=10IWAE · Binarized MNIST testNLL_te: 81.13 -> 81.04Improved
Use H-IWAE with α=0 instead of IWAE at K=10IWAE · Binarized OMNIGLOT testNLL_te: 98.48 -> 98.80Hurt
Use H-IWAE with encoder updated twice per decoder update (ablation)H-IWAE (α=1, K=5) · Caltech101 Silhouettes testNLL_te: 106.62:0.09 -> 104.16:0.64Improved
Increase K from 1 to 10 for H-IWAE with α=1 (ablation)H-IWAE · Binarized MNIST testNLL_te: 81.89 -> 81.04Improved
Increase K from 1 to 10 for H-IWAE with α=1 (ablation)H-IWAE · Binarized OMNIGLOT testNLL_te: 100.57 -> 99.04Improved
Use arithmetic averaging (α=0) instead of α=1 at K=5 (ablation)H-IWAE · Binarized MNIST testNLL_te: 81.16 -> 81.93Hurt
Use balanced weighting (α=1) instead of arithmetic averaging (α=0) at K=5 (ablation)H-IWAE · Binarized OMNIGLOT testNLL_te: 99.23 -> 99.21No clear effect
Train with a shared common random number rather than independent latent factors (ablation)Hierarchical importance sampler · Toy posterior experimentvariance of importance estimatorImproved
Use a Markov transition proposal instead of the hierarchical common-factor proposal (ablation)Hierarchical importance sampler · Toy posterior experimentproposal compensationHurt

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