AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

No Free Lunch: Non-Asymptotic Analysis of Prediction-Powered Inference

Pranav Mani, Peng Xu, Zachary Chase Lipton, Michael Oberst

ICML 2026 · Probabilistic and scientific modeling › Molecules and proteins · approach: Prediction-powered and conformal inference · 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 single-sample PPI++ (no sample splitting) instead of classical estimator for interval constructionPPI++ confidence intervals · AlphaFold, n = 20coverage: realized coverage 87% at n = 20Hurt
add cross-fitting (sample splitting) to PPI++ (ablation)PPI++ · AlphaFoldinterval coverageImproved
lower pseudo-label correlation below roughly 1/sqrt(n)PPI++ vs classical estimator · Gaussian labelsvariance: improvement requires correlation above 1/sqrt(n - 2)Hurt
use cross-fit instead of single-sample PPI++PPI++ · Gaussian labelscorrelation threshold for improvement: (n - 2)^-1/2 -> (n/2 - 2)^-1/2Hurt
increase labeled sample size nPPI++ with imperfect pseudo-labels · AlphaFoldMSE difference vs classicalImproved

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