AI Paper Atlas

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

From Monte Carlo to Las Vegas: Improving Restricted Boltzmann Machine Training Through Stopping Sets

Pedro Savarese, Mayank Kakodkar, Bruno Ribeiro

AAAI 2018 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Sequential Monte Carlo for inference · 3 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 LVS-1 instead of CD-10RBM with 32 hidden neurons · MNIST testingaverage log-likelihood: -153.4 -> -133.3Improved
Use LVS-1 instead of PCD-10RBM with 32 hidden neurons · MNIST testingaverage log-likelihood: -138.5 -> -133.3Improved
Use LVS-1 instead of CD-10RBM with 25 hidden neurons · MNIST testingaverage log-likelihood: -155.6 -> -137.5Improved
Use LVS-1 instead of PCD-10RBM with 25 hidden neurons · MNIST testingaverage log-likelihood: -146.7 -> -137.5Improved
Vary LVS maximum tour length among K=1, K=3, and K=10 (ablation)RBM with 32 hidden neurons · MNISTaverage log-likelihood: -134.0 (1.0), -133.7 (0.8), -133.3 (1.0) training; -133.3 (1.0), -132.9 (0.7), -132.6 (1.0) testingNo clear effect
Vary LVS maximum tour length among K=1, K=3, and K=10 (ablation)RBM with 25 hidden neurons · MNISTaverage log-likelihood: -138.3 (1.3), -138.2 (1.0), -138.1 (1.1) training; -137.5 (1.4), -137.5 (1.1), -137.4 (1.2) testingNo clear effect
Use a larger stopping set (ablation)MCLV/LVS tours on RBM with 32 hidden neurons · MNIST training data, tour-length analysisprobability of finishing in one stepImproved
Use learning rates from 10^{-1} to 1 rather than small rates such as 10^{-4} (ablation)LVS-K on RBM with 25 hidden neurons · MNISTconvergence and performanceImproved
Use small learning rates such as 10^{-4} (ablation)LVS-K on RBM with 25 hidden neurons · MNISTtraining speedHurt

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