AI Paper Atlas

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

Decision-Theoretic Approaches for Improved Learning-Augmented Algorithms

Spyros Angelopoulos, Christoph Dürr, Georgii Melidi

ICLR 2026 · Learning theory and algorithms › Prediction and decision losses · approach: Algorithms with explicit predictors

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 distance-based and CVaR thresholds instead of the BP_rho familylearning-augmented ski rental · Ski rental (b=10, r=5, delta=0.9)average performance ratio: 1.677 -> 1.337Improved
increase CVaR risk-aversion alpha from 0.1 to 0.9 (ablation)CVaR algorithm, ski rental · Ski rental (b=10, r=5, delta=0.9)average performance ratio: 1.340 -> 1.367Hurt
increase CVaR risk-aversion alpha from 0.1 to 0.9 (ablation)CVaR algorithm, one-max search · One-max search (M=1000, r=100, delta=0.9)average performance ratio: 9.771 -> 6.022Improved
increase CVaR risk-aversion alpha from 0.1 to 0.9 (ablation)CVaR algorithm, one-max search · One-max search (M=1000, r=100, delta=0.9)expected profit: 35.795 -> 27.500Hurt
use Max or Avg distance thresholds instead of Pareto-optimal PO1 and delta-Tolone-max search · One-max search (M=1000, r=100, delta=0.9)average performance ratio: 4.630 -> 4.394Improved
use CVaR thresholds instead of delta-Tolone-max search · One-max search (M=1000, r=100, delta=0.9)expected profit: 5.475 -> 27.500Improved
use CVaR thresholds instead of PO1one-max search · One-max search (M=1000, r=100, delta=0.9)average performance ratio: 4.630 -> 6.022Hurt
shrink the prediction range or concentrate the weight function around y (ablation)Max, Avg, CVaR algorithms · appendix parameter studyperformanceImproved

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