AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

GaSPing for Utility

Mengyang Gu, Debarun Bhattacharjya, Dharmashankar Subramanian

AAAI 2020 · Learning theory and algorithms › Prediction and decision losses · approach: Adaptive testing and experiments · 0 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 GaSP instead of linear interpolationutility estimator · Synthetic noise-free n=7, alpha=0.7out-of-sample MSE: 9.5 × 10−6 -> 2.8 × 10−7Improved
use GaSP instead of linear interpolationutility estimator · Synthetic noise-free n=7, alpha=2.5out-of-sample MSE: 3.8 × 10−4 -> 5.0 × 10−6Improved
use GaSP instead of exponential parametric fitutility estimator · Synthetic noise-free n=7, alpha=1.5out-of-sample MSE: 3.2 × 10−4 -> 5.5 × 10−6Improved
use GaSP instead of QPDutility estimator · Synthetic noise-free n=7, alpha=2.5out-of-sample MSE: 2.8 × 10−3 -> 5.0 × 10−6Improved
use GaSP with a misspecified mean basis (x^0.5) (ablation)GaSP · Synthetic noise-free power utilityout-of-sample MSENo clear effect
use GaSP instead of linear interpolation under additive noiseutility estimator · Synthetic noisy n=10, alpha=0.7AvgMSE: 1.8 × 10−5 -> 9.7 × 10−6Improved
use GaSP instead of linear interpolation under additive noiseutility estimator · Synthetic noisy n=10, alpha=2.5AvgMSE: 1.9 × 10−4 -> 1.3 × 10−4Improved
add noise to assessments (noise-free to noisy)all methods · Synthetic power utilityMSEHurt
use GaSP second-derivative posterior for curvature instead of LI slope changescurvature classification · Synthetic noisy exponential utilities, n=15concavity classificationImproved
use GaSP instead of linear interpolationutility estimator · Single-attribute real data, loss domainAvgMSE: 9.7 × 10−4 -> 8.9 × 10−4Improved
use GaSP instead of linear interpolationutility estimator · Single-attribute real data, gain domainAvgMSE: 8.2 × 10−5 -> 7.4 × 10−5Improved
use GaSP instead of power/exponential parametric fitutility estimator · Single-attribute real data, loss domainAvgMSE: 1.7 × 10−3 -> 8.9 × 10−4Improved

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