AI Paper Atlas

Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes

Neural Diffusion Processes

Vincent Dutordoir, Alan Saul, Zoubin Ghahramani, Fergus Simpson

ICML 2023 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Infinite-width networks as Gaussian processes · 2 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 NDP (diffusion over function marginals with bi-dimensional attention) instead of NP baselinesNDP vs NPs on synthetic GP regression · Squared Exponential and Matern-5/2, D=1-3test log-likelihoodMixed
NDP with bi-dimensional attention vs GNP on higher-dimensional GP regressionNDP · Squared Exponential D=2,3test log-likelihood: -0.67 vs -0.98 (D=2); -1.16 vs -1.36 (D=3)Improved
Use NDP instead of GNP on Matern-5/2 D=1 regressionNDP · Matern-5/2 D=1test log-likelihood: -0.00 vs 0.14Hurt
Hyperparameter marginalisation via NDP trained on Matern lengthscale priorNDP · GP samples with lengthscale priorqualitative lengthscale posteriorImproved
Bayesian optimisation with NDP surrogate (no retraining) instead of retrained GPRNDP · Black-box optimisation, dimensions 3-6regretNo 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