AI Paper Atlas

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

Exchangeable Generative Models with Flow Scans

Christopher Bender, Kevin O'Connor, Yang Li, Juan Garcia, Junier Oliva, Manzil Zaheer

AAAI 2020 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Expressive invertible architectures · 6 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 FlowScan instead of the strongest reported baseline, NSExchangeable density estimation · SyntheticPPLL: -1.07 -> 0.14Improved
Use FlowScan instead of the strongest reported baseline, NSExchangeable density estimation · AirplanesPPLL: 4.09 -> 4.81Improved
Use FlowScan instead of the strongest reported baseline, NSExchangeable density estimation · ChairsPPLL: 2.02 -> 2.58Improved
Use FlowScan instead of the strongest reported baseline, NSExchangeable density estimation · ModelNet10PPLL: 2.12 -> 3.01Improved
Use FlowScan instead of the strongest reported baseline, NSExchangeable density estimation · ModelNet10aPPLL: 2.82 -> 3.58Improved
Use FlowScan instead of the strongest reported baseline, NSExchangeable density estimation · CaudatePPLL: 4.49 -> 4.87Improved
Use FlowScan instead of the strongest reported baseline, NSExchangeable density estimation · ThalamusPPLL: 2.69 -> 3.12Improved
Use FlowScan instead of the strongest reported baseline, NSExchangeable density estimation · SpatialMNISTPPLL: -5.37 -> -5.26Improved
Add convolution-based Set-Coupling to BRUNO while retaining the i.i.d. base likelihoodMNIST image sets · MNISTPPLL: -643.6 -> -634.8Improved
Add sorting, scan likelihood, and 3d convolution-based correspondence couplingSet-Coupling model · MNISTPPLL: -634.8 -> -621.7Improved
Add correspondence coupling (ablation)FlowScan on ModelNet10 · ModelNet10PPLL: 2.67 -> 3.01Improved
Add equivariant flow transformation (ablation)FlowScan on ModelNet10 · ModelNet10PPLL: 2.34 -> 2.67Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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