AI Paper Atlas

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

Deep Stochastic Processes via Functional Markov Transition Operators

Jin Xu, Emilien Dupont, Kaspar Märtens, Tom Rainforth, Yee Whye Teh

NeurIPS 2023 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Tractable probabilistic models · 0 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
MNPs (7 transition steps) instead of NPsMNPs · 1D regression, RBF kernelmarginal log-likelihood: 0.935 -> 2.491Improved
MNPs instead of NPsMNPs · 1D regression, Matern kernelmarginal log-likelihood: 1.115 -> 2.290Improved
MNPs instead of NPsMNPs · 1D regression, periodic kernelmarginal log-likelihood: 0.356 -> 0.594Improved
MNPs instead of NPs on non-GP monotonic functionsMNPs · Monotonic functionsmarginal log-likelihood: 1.823 -> 2.755Improved
MNPs instead of CBPs (Gaussian copula) on convex functionsMNPs · Convex functionsmarginal log-likelihood: 4.268 -> 5.582Improved
MNPs instead of GPs on SDE samplesMNPs · SDEsmarginal log-likelihood: 1.719 -> 1.942Improved
MNPs instead of GPs/CBPs on GP-sampled RBF dataMNPs · RBF kernelmarginal log-likelihood: 2.844 -> 2.491Hurt
MNPs instead of CBPs on periodic kernel dataMNPs · Periodic kernelmarginal log-likelihood: 0.169 -> 0.594Improved
MNPs instead of NPs, cumulative regret at high exploration delta=0.99MNPs · Wheel banditcumulative regret: 22.13 -> 5.46Improved
MNPs instead of NPs, cumulative regret at delta=0.5MNPs · Wheel banditcumulative regret: 1.60 -> 1.08Improved
MNPs instead of NPs, simple regret at delta=0.5MNPs · Wheel banditsimple regret: 1.04 -> 1.14No clear effect
MNPs instead of NPs, simple regret at delta=0.99MNPs · Wheel banditsimple regret: 21.45 -> 5.22Improved

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