paper-with-me

Papers

Large-scale probabilistic predictors with and without guarantees of validity

2015-11-01 · NeurIPS 2015 12 · Vladimir Vovk, Ivan Petej, Valentina Fedorova

This paper studies theoretically and empirically a method of turning machine-learning algorithms into probabilistic predictors that automatically enjoys a property of validity (perfect calibration) and is computationally efficient. The price to pay for perfect calibration is that these probabilistic predictors produce imprecise (in practice, almost precise for large data sets) probabilities. When these imprecise probabilities are merged into precise probabilities, the resulting predictors, while losing the theoretical property of perfect calibration, are consistently more accurate than the existing methods in empirical studies.

📄 PDF Abstract BibTeX arXiv:1511.00213

Code (1)

ip200/venn-abers

Tasks

BIG-bench Machine Learning

Similar Papers 제목 키워드 기반

Multi-class probabilistic classification using inductive and cross Venn-Abers predictors

2017-06-16 · Proceedings of the Sixth Workshop on Conformal and Probabilistic Prediction and Applications, PMLR 60:1-2 2017 6 · Valery Manokhin

Inductive (IVAP) and cross (CVAP) Venn–Abers predictors are computationally efficient algorithms for probabilistic prediction in binary classification problems. We present a new approach to multi-class probability estima…

Binary ClassificationClassificationClassifier calibrationConformal Prediction+1

Quantile Regression, Variational Autoencoders, and Diffusion Models for Uncertainty Quantification: A Spatial Analysis of Sub-seasonal Wind Speed Prediction

2025-10-19 · Ganglin Tian, Anastase Alexandre Charantonis, Camille Le Coz, Alexis Tantet 외 arxiv

This study aims to improve the spatial representation of uncertainties when regressing surface wind speeds from large-scale atmospheric predictors for sub-seasonal forecasting. Sub-seasonal forecasting often relies on la…

Zono-Conformal Prediction: Zonotope-Based Uncertainty Quantification for Regression and Classification Tasks

2025-08-14 · Laura Lützow, Michael Eichelbeck, Mykel J. Kochenderfer, Matthias Althoff arxiv

Conformal prediction is a popular uncertainty quantification method that augments a base predictor to return sets of predictions with statistically valid coverage guarantees. However, current methods are often computatio…

Modeling Probabilistic Reduction using Information Theory and Naive Discriminative Learning

2025-06-11 · Anna Stein, Kevin Tang

This study compares probabilistic predictors based on information theory with Naive Discriminative Learning (NDL) predictors in modeling acoustic word duration, focusing on probabilistic reduction. We examine three model…

Constrained Sampling and Counting: Universal Hashing Meets SAT Solving

2015-12-21 · Kuldeep S. Meel, Moshe Vardi, Supratik Chakraborty, Daniel J. Fremont 외

Constrained sampling and counting are two fundamental problems in artificial intelligence with a diverse range of applications, spanning probabilistic reasoning and planning to constrained-random verification. While the …