AWhat changed
Used triangular autoregressive transforms to enrich variational posteriors and construct flexible density estimators, exploiting complementary fast directions in IAF and MAF.
Scientific scope
Used triangular autoregressive transforms to enrich variational posteriors and construct flexible density estimators, exploiting complementary fast directions in IAF and MAF. Two related original contributions with separate bylines. IAF supports parallel sampling and density evaluation for its own tracked samples, not fast inversion for every externally given point; MAF supports fast density evaluation but dimension-sequential sampling. A triangular Jacobian does not remove this direction-dependent cost.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Two related original contributions with separate bylines. IAF supports parallel sampling and density evaluation for its own tracked samples, not fast inversion for every externally given point; MAF supports fast density evaluation but dimension-sequential sampling. A triangular Jacobian does not remove this direction-dependent cost.
Contributors
- Source-listed authors and technical contributors · SCIENCE: Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.
- Improving Variational Inference with Inverse Autoregressive Flow
- Masked Autoregressive Flow for Density Estimation
Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.
Full scientific record · Browse contribution grades · Request a correction