AI Paper Atlas

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

The Implicit Delta Method

Nathan Kallus, James McInerney

NeurIPS 2022 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Regression uncertainty quantification · 1 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 FDIDM instead of bootstrap to estimate uncertaintyNeural network classifier · Vehicleruntime: 806 -> 39 secondsImproved
Use FDIDM instead of bootstrap to estimate uncertaintyNeural network classifier · Waveformruntime: 2,334 -> 129 secondsImproved
Use FDIDM instead of bootstrap to estimate uncertaintyNeural network classifier · Satelliteruntime: 3,192 -> 111 secondsImproved
Use FDIDM instead of bootstrap to estimate uncertaintyNeural network classifier · MNISTruntime: 7,164 -> 303 secondsImproved
Set finite-difference width to λ=0.512 rather than the delta-method estimate (ablation)FDIDM · Quadratic synthetic taskroot mean squared error of variance estimateImproved
Use very small finite-difference widths λ<0.01 (ablation)FDIDM · Quadratic synthetic taskroot mean squared error of variance estimateHurt
Increase KL down-weighting T and introduce more reconstruction-quality variance (ablation)Variational autoencoder · MNISTreconstruction qualityImproved

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