AI Paper Atlas

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

Hedging on the Frontier: Learning New Tasks with Few Samples

Tobias Wegel, Federico Di Gennaro, Geelon So, Fanny Yang

ICML 2026 · Learning theory and algorithms › Prediction and decision losses · approach: Active learning and subset selection · 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
restrict ERM to the Pareto frontier of source benchmarks (ERM-Pareto)ERM on a model zoo · HELM Lite (K=3 sources, small target n)mean excess riskImproved
restrict ERM to the Pareto frontier of source benchmarks (ERM-Pareto)ERM on a model zoo · VHELM (K=3 sources, small target n)mean excess riskImproved
use adaptive margin ERM instead of ERM over all modelsERM-all · HELM and VHELM (K=3)mean excess riskImproved
restrict ERM to the Pareto set (versus all models) at large target sample size (ablation)ERM-Pareto · HELM and VHELM (K=1, large n)mean excess riskHurt
grow the candidate set with n (adaptive margin) instead of fixed Pareto set (ablation)ERM-Pareto · HELM and VHELM (various K)mean excess riskImproved
use Min-Max source-only selection instead of using target samples (ablation)Min-Max baseline · HELM (K=1)mean excess riskNo clear effect
increase the number of source benchmarks K (ablation)frontier-biased ERM · HELM (K=1..6) and VHELM (K=1..8)mean excess riskNo clear effect

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