paper-with-me

Papers

Active Multiple-Prediction-Powered Inference

2026-05-08 · Nicholas Brawand, Nima Leclerc, Anhthy Ngo, Matthew Peterson, Sriram Vishwanath, Laith Alhussein, Ben Wellner arxiv

Post-deployment monitoring of healthcare AI requires statistically valid, label-efficient methods, but gold-standard labels from clinician chart review are expensive. Prediction-powered inference (PPI) and active statistical inference (ASI) reduce label cost by combining a small labeled sample with abundant model predictions, but both are restricted to a single predictor, a poor fit for modern clinical pipelines that have multiple predictors of differing cost and accuracy available at inference time. We propose Active Multiple-Prediction-Powered Inference (AM-PPI), which routes each instance to a cost-appropriate predictor subset, samples gold-standard labels in proportion to the chosen subset's residual uncertainty, and reweights predictions to minimize estimator variance, all under a single deployment-time budget. AM-PPI generalizes ASI to leverage multiple predictors and extends Multiple-PPI from global per-predictor allocation to per-instance adaptive routing. We derive closed-form Karush-Kuhn-Tucker (KKT) conditions for all three decisions and prove, via biconvexity and strong duality, that the resulting fixed point is a global optimum despite the joint problem being non-jointly-convex. We establish asymptotic normality with valid coverage, minimum-variance unbiasedness within the linear-prediction augmented inverse propensity weighted (AIPW) class, and a closed-form criterion identifying when multiple predictors help. On synthetic data and three healthcare monitoring tasks, AM-PPI produces 10 to 40 percent narrower confidence intervals (CIs) than single-predictor ASI in the budget regime where routing matters, and matches the better baseline elsewhere.

📄 PDF Abstract BibTeX arXiv:2605.08429

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Industrializing Prediction-Powered Inference: The GLIDE Library for Reliable GenAI and Agentic Systems Evaluation

2026-05-29 · Grégoire Martinon, Ibrahim Merad, Mohammed Raki arxiv

Reliable evaluation of agentic systems requires unbiased estimates with valid uncertainty, but standard practice navigates between costly human annotation and biased LLM-as-judge proxies. Prediction-powered inference (PP…

Extending Prediction-Powered Inference through Conformal Prediction

2025-10-17 · Daniel Csillag, Pedro Dall'Antonia, Claudio José Struchiner, Guilherme Tegoni Goedert arxiv

Prediction-powered inference is a recent methodology for the safe use of black-box ML models to impute missing data, strengthening inference of statistical parameters. However, many applications require strong properties…

Prediction-Powered Inference

2023-01-23 · Anastasios N. Angelopoulos, Stephen Bates, Clara Fannjiang, Michael I. Jordan 외

Prediction-powered inference is a framework for performing valid statistical inference when an experimental dataset is supplemented with predictions from a machine-learning system. The framework yields simple algorithms …

AstronomyPredictionregressionvalid

Prediction-Powered E-Values

2025-02-06 · Daniel Csillag, Claudio José Struchiner, Guilherme Tegoni Goedert

Quality statistical inference requires a sufficient amount of data, which can be missing or hard to obtain. To this end, prediction-powered inference has risen as a promising methodology, but existing approaches are larg…

Causal DiscoveryChange Point DetectionPrediction

Multiple-Prediction-Powered Inference

2026-03-28 · Charlie Cowen-Breen, Alekh Agarwal, Stephen Bates, William W. Cohen 외 arxiv

Statistical estimation often involves tradeoffs between expensive, high-quality measurements and a variety of lower-quality proxies. We introduce Multiple-Prediction-Powered Inference (MultiPPI): a general framework for …