Multiple-Prediction-Powered Inference

• URL: http://arxiv.org/abs/2603.27414v1
• Date: Sat, 28 Mar 2026 21:24:00 GMT
• Title: Multiple-Prediction-Powered Inference
• Abstract summary: This work provides theoretical guarantees about the minimax optimality, finite-sample performance, and normality of the MultiPPI estimator.<n>We show that MultiPPI consistently achieves lower estimation error than existing baselines.
• Score: 57.30769275944024
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 constructing statistically efficient estimates by optimally allocating resources across these diverse data sources. This work provides theoretical guarantees about the minimax optimality, finite-sample performance, and asymptotic normality of the MultiPPI estimator. Through experiments across three diverse large language model (LLM) evaluation scenarios, we show that MultiPPI consistently achieves lower estimation error than existing baselines. This advantage stems from its budget-adaptive allocation strategy, which strategically combines subsets of models by learning their complex cost and correlation structures.

Related papers

• Split the Differences, Pool the Rest: Provably Efficient Multi-Objective Imitation [49.86232017439639]
  We introduce Multi-Output Augmented Behavioral Cloning (MA-BC)<n>MA-BC partitions divergent expert data while pooling state-action pairs where no behavior conflict is observed.<n>We establish a novel lower bound for multi-objective imitation learning, demonstrating that MA-BC is minimax optimal.
  arXiv  Detail & Related papers  (2026-05-12T11:49:08Z)
• MMR1: Enhancing Multimodal Reasoning with Variance-Aware Sampling and Open Resources [113.33902847941941]
  Variance-Aware Sampling (VAS) is a data selection strategy guided by Variance Promotion Score (VPS)<n>We release large-scale, carefully curated resources containing 1.6M long CoT cold-start data and 15k RL QA pairs.<n> Experiments across mathematical reasoning benchmarks demonstrate the effectiveness of both the curated data and the proposed VAS.
  arXiv  Detail & Related papers  (2025-09-25T14:58:29Z)
• Towards Universal Debiasing for Language Models-based Tabular Data Generation [16.31419748401203]
  We introduce a universal debiasing framework that minimizes group-level dependencies by simultaneously reducing the mutual information between advantaged and protected attributes.<n>Our framework effectively balances fairness and utility, offering a scalable and practical solution for debiasing in high-stakes applications.
  arXiv  Detail & Related papers  (2025-09-20T00:06:53Z)
• Generative Distribution Prediction: A Unified Approach to Multimodal Learning [4.3108820946281945]
  We introduce Generative Distribution Prediction (GDP) to enhance predictive performance across structured and unstructured modalities.<n>GDP is model-agnostic, compatible with any high-fidelity generative model, and supports transfer learning for domain adaptation.<n>We empirically validate GDP on four supervised learning tasks-tabular data prediction, question answering, image captioning, and adaptive quantile regression-demonstrating its versatility and effectiveness across diverse domains.
  arXiv  Detail & Related papers  (2025-02-10T22:30:35Z)
• A Unified Comparative Study with Generalized Conformity Scores for Multi-Output Conformal Regression [1.747623282473278]
  We present a unified comparative study of nine conformal methods with different multi-output base models.<n>We also introduce two novel classes of conformity scores for multi-output regression.<n>One class is compatible with any generative model, while the other is computationally efficient, leveraging the properties of invertible generative models.
  arXiv  Detail & Related papers  (2025-01-17T20:13:24Z)
• Generalization Bounds of Surrogate Policies for Combinatorial Optimization Problems [53.03951222945921]
  We analyze smoothed (perturbed) policies, adding controlled random perturbations to the direction used by the linear oracle.<n>Our main contribution is a generalization bound that decomposes the excess risk into perturbation bias, statistical estimation error, and optimization error.<n>We illustrate the scope of the results on applications such as vehicle scheduling, highlighting how smoothing enables both tractable training and controlled generalization.
  arXiv  Detail & Related papers  (2024-07-24T12:00:30Z)
• Multivariate Stochastic Dominance via Optimal Transport and Applications to Models Benchmarking [21.23500484100963]
  We introduce a statistic that assesses almost dominance under the framework of Optimal Transport with a smooth cost. We also propose a hypothesis testing framework as well as an efficient implementation using the Sinkhorn algorithm. We showcase our method in comparing and benchmarking Large Language Models that are evaluated on multiple metrics.
  arXiv  Detail & Related papers  (2024-06-10T16:14:50Z)
• Quantifying & Modeling Multimodal Interactions: An Information Decomposition Framework [89.8609061423685]
  We propose an information-theoretic approach to quantify the degree of redundancy, uniqueness, and synergy relating input modalities with an output task. To validate PID estimation, we conduct extensive experiments on both synthetic datasets where the PID is known and on large-scale multimodal benchmarks. We demonstrate their usefulness in (1) quantifying interactions within multimodal datasets, (2) quantifying interactions captured by multimodal models, (3) principled approaches for model selection, and (4) three real-world case studies.
  arXiv  Detail & Related papers  (2023-02-23T18:59:05Z)
• A Unified Framework for Multi-distribution Density Ratio Estimation [101.67420298343512]
  Binary density ratio estimation (DRE) provides the foundation for many state-of-the-art machine learning algorithms. We develop a general framework from the perspective of Bregman minimization divergence. We show that our framework leads to methods that strictly generalize their counterparts in binary DRE.
  arXiv  Detail & Related papers  (2021-12-07T01:23:20Z)
• Optimal Off-Policy Evaluation from Multiple Logging Policies [77.62012545592233]
  We study off-policy evaluation from multiple logging policies, each generating a dataset of fixed size, i.e., stratified sampling. We find the OPE estimator for multiple loggers with minimum variance for any instance, i.e., the efficient one.
  arXiv  Detail & Related papers  (2020-10-21T13:43:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.