AI Paper Atlas

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

A Risk Decomposition Framework for Pre-hoc Fine-tuning Prediction

Yuxiang Luo, Chen Wang, Nan Tang

ICML 2026 · Learning theory and algorithms › Prediction and decision losses · approach: Distributionally robust optimization · 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
probe fine-tuning for more optimization steps on Dynamic-Critical tasks such as GSM8Kpre-hoc fine-tuning predictors · GSM8K-like reasoning fine-tuning tasksprediction uncertaintyImproved
probe deeper on Static-Sufficient tasks such as SST-2pre-hoc fine-tuning predictors · SST-2 and GLUE-style classificationprediction uncertaintyNo clear effect
probe deeper on Noise-Dominant tasks with label noisepre-hoc fine-tuning predictors · noisy or ambiguous supervision tasksprediction uncertaintyNo clear effect
increase probing depth in general (ablation)budget-optimal probing · all three regimesnormalized marginal gain of probingMixed
use shallow fixed-step probing on a Dynamic-Critical taskprobing predictors · GSM8K-like tasksprediction stabilityHurt

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