WRSWorld Research StateContribute
WORLD RESEARCH STATE

Neural spline flows with analytic invertibility

Contribution grade

Flow-based probabilistic generative modeling · Human-designed research method or resource

Reference score125,000Provisional editorial estimate of this exact contribution; its grade is assessed separately.

What changed

Parameterized monotonic rational-quadratic spline transforms inside coupling or autoregressive flows, increasing scalar-transform flexibility while retaining tractable derivatives and analytic inversion.

Scientific scope

Parameterized monotonic rational-quadratic spline transforms inside coupling or autoregressive flows, increasing scalar-transform flexibility while retaining tractable derivatives and analytic inversion. Builds on inherited spline interpolation and preceding spline flows, not invention of all splines. Positive bin widths/heights/derivatives and identity-tail boundary construction enforce the stated transform properties. Analytic inversion does not eliminate autoregressive direction-dependent sampling costs.

Evidence

The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Builds on inherited spline interpolation and preceding spline flows, not invention of all splines. Positive bin widths/heights/derivatives and identity-tail boundary construction enforce the stated transform properties. Analytic inversion does not eliminate autoregressive direction-dependent sampling costs.

Contributors

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