AI Paper Atlas

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

Hamiltonian Variational Auto-Encoder

Anthony L Caterini, Arnaud Doucet, Dino Sejdinovic

NeurIPS 2018 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Sequential Monte Carlo for 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
Add Hamiltonian dynamics with free tempering (K=15, epsilon fixed across layers)Convolutional VAE · Binarized MNIST testNLL: 83.20 -> 82.78Improved
Use fixed rather than no tempering at K=5 with epsilon fixed across layers (ablation)HVAE · Binarized MNIST testNLL: 83.68 -> 83.26Improved
Use fixed rather than no tempering at K=10 with epsilon fixed across layers (ablation)HVAE · Binarized MNIST testNLL: 83.40 -> 83.26Improved
Use fixed rather than no tempering at K=15 with epsilon fixed across layers (ablation)HVAE · Binarized MNIST testNLL: 83.82 -> 83.56Hurt
Use free rather than fixed tempering with epsilon fixed across layers (ablation)HVAE · Binarized MNIST testNLL: 83.26 -> 83.09 (K=5); 83.26 -> 82.97 (K=10); 83.56 -> 82.78 (K=15); 83.18 -> 82.93 (K=20)Improved
Vary leapfrog step size across layers rather than keeping it fixed (free tempering) (ablation)HVAE · Binarized MNIST testNLL: 83.09 -> 83.01 (K=5); 82.97 -> 82.62 (K=10); 82.78 -> 82.62 (K=15); 82.93 -> 82.83 (K=20)Improved
Increase leapfrog steps from K=15 to K=20 under free tempering with fixed epsilon (ablation)HVAE · Binarized MNIST testNLL: 82.78 -> 82.93Hurt
Add time-inhomogeneous tempering instead of fixing beta_0 to 1 (ablation)HVAE · Gaussian model parameter estimationsquared parameter errorImproved
Use HVAE rather than mean-field variational BayesGaussian model · Gaussian model parameter estimationsquared parameter errorImproved
Use HVAE rather than planar normalizing flowGaussian model · Gaussian model parameter estimationsquared parameter errorMixed

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