AI Paper Atlas

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

Wasserstein Training of Restricted Boltzmann Machines

Grégoire Montavon, Klaus-Robert Müller, Marco Cuturi

NeurIPS 2016 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Posterior sampling with diffusion guidance

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
Train RBM with smoothed Wasserstein distance objective (with KL pretraining) instead of KL/MLERestricted Boltzmann machine · MNIST-small, PLANTS, MNIST-code: Wasserstein distance evaluationsmooth Wasserstein distance W_gamma to test dataImproved
Train RBM with Wasserstein objective instead of standard KL trainingRestricted Boltzmann machine · Data completion on MNIST-small, PLANTS, MNIST-codeexpected Hamming errorImproved
Train RBM with Wasserstein objective instead of standard KL trainingRestricted Boltzmann machine · Data denoising on MNIST-small, PLANTS, MNIST-codeexpected Hamming errorImproved
Omit KL pretraining before Wasserstein training (ablation)RBM-W · MNIST-small, PLANTS, MNIST-codeWasserstein distanceHurt
Use a smaller KL weighting lambda (too little KL regularization) (ablation)RBM-W · MNIST-small, PLANTS, MNIST-codeWasserstein distanceHurt
Increase Wasserstein smoothing parameter gamma (ablation)RBM-W · MNIST-small, PLANTS, MNIST-codedegree of shrinkage of learned distributionNo clear effect

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