AI Paper Atlas

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

Tensor Monte Carlo: Particle Methods for the GPU era

Laurence Aitchison

NeurIPS 2019 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Importance sampling and quadrature · 9 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 TMC instead of IWAE with the same particle countMNIST multi-layer VAE · MNISTvariational lower bound: 20 -> 20^5Improved
Use TMC instead of IWAEGaussian latent-variable toy model · Gaussian toy experiment, N=128log-marginal likelihood boundImproved
Use TMC instead of SMCGaussian latent-variable toy model · Gaussian toy experimentlog-marginal likelihood boundImproved
Use TMC instead of SMCGaussian latent-variable toy model · Gaussian toy experimentruntimeImproved
Use a non-factorised rather than factorised proposal (ablation)TMC · Correlated Gaussian latent chain, N=100log-marginal likelihood boundImproved
Train with TMC rather than IWAEMNIST multi-layer VAE · MNISTvariational lower boundImproved
Evaluate an IWAE-trained model with TMC rather than IWAE (ablation)MNIST multi-layer VAE trained with IWAE · MNISTvariational lower boundImproved
Add STL to TMC (ablation)MNIST multi-layer VAE · MNISTvariational lower boundHurt
Add DReGs to TMC (ablation)MNIST multi-layer VAE · MNISTvariational lower boundHurt
Add DReGs to TMC (ablation)MNIST multi-layer VAE · MNISTruntimeHurt
Increase recognition-model capacity from factorised or small non-factorised to large non-factorised (ablation)TMC and IWAE · MNISTTMC-bound advantage over IWAEMixed

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