AI Paper Atlas

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

Estimating Regression Predictive Distributions with Sample Networks

Ali Harakeh, Jordan Sir Kwang Hu, Naiqing Guan, Steven Waslander, Liam Paull

AAAI 2023 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Single-model predictive uncertainty · 5 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
represent predictions as learned samples and train with the Energy Score instead of a parametric distributionSampleNet · WeatherEnergy Score: 0.594 ± 0.032 -> 0.106 ± 0.002Improved
represent predictions as learned samples and train with the Energy Score instead of a parametric distributionSampleNet · TrafficEnergy Score: 133.884 ± 3.138 -> 12.562 ± 0.389Improved
use learned samples with flexible predictive distributionsSampleNet · NYUv2Gaussian NLL: 7.237 ± 6.85e-1 -> 1.398 ± 1.22e-3Improved
use Sinkhorn regularization with η=1.0 (ablation)SampleNet · NYUv2Average variance, All: 0.0157 -> 0.0115Improved
remove Sinkhorn regularization (η=0) (ablation)SampleNet · NYUv2Energy Score: 0.2371 ± 5.43e-4 -> 0.2354 ± 4.01e-3Hurt
increase Sinkhorn regularization strength from η=0 to η=5 (ablation)SampleNet · WeatherEnergy Score: 0.117 ± 0.002 -> 0.106 ± 0.002Improved
increase Sinkhorn regularization strength (ablation)SampleNet · TrafficEnergy ScoreNo clear effect
increase minibatch loss sample size K (ablation)SampleNet · TrafficEnergy ScoreImproved
increase the number of minibatch loss repetitions L (ablation)SampleNet · TrafficEnergy ScoreImproved
increase the number of predicted samples M (ablation)SampleNet · Weather and TrafficEnergy ScoreNo clear effect
increase output samples from M=25 to M=50 (ablation)SampleNet · NYUv2Energy Score: 0.2371 -> 0.2381Hurt
remove Sinkhorn regularization (ablation)SampleNet · NYUv2δ1: 0.8900 -> 0.8891Hurt

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