Theory and Applications of Proper Scoring Rules

Abstract

We give an overview of some uses of proper scoring rules in statistical inference, including frequentist estimation theory and Bayesian model selection with improper priors.

13 pages

References in corpus (2)

• Minimum scoring rule inference
• Bayesian Model Selection Based on Proper Scoring Rules

Cited by in corpus (35)

• A review of predictive uncertainty estimation with machine learning
• Minimum scoring rule inference
• Generative Adversarial Nets from a Density Ratio Estimation Perspective
• Statistical Inference for Generative Models with Maximum Mean Discrepancy
• Bayesian Model Selection Based on Proper Scoring Rules
• Objective Bayesian inference with proper scoring rules
• Scoring Interval Forecasts: Equal-Tailed, Shortest, and Modal Interval
• Twin Neural Network Regression
• Minimum Stein Discrepancy Estimators
• From Proper Scoring Rules to Max-Min Optimal Forecast Aggregation
• Properization: Constructing Proper Scoring Rules via Bayes Acts
• Marginally-calibrated deep distributional regression
• Comparing Sequential Forecasters
• Bayesian Estimate of Mean Proper Scores for Diversity-Enhanced Active Learning
• Proper Scoring Rules for Multivariate Probabilistic Forecasts based on Aggregation and Transformation
• Robust approximate Bayesian inference
• Generalized Bayesian Likelihood-Free Inference
• Superior Scoring Rules for Probabilistic Evaluation of Single-Label Multi-Class Classification Tasks
• Comparative evaluation of point process forecasts
• Exponential Series Approaches for Nonparametric Graphical Models
• Binary Scoring Rules that Incentivize Precision
• Object Detection as Probabilistic Set Prediction
• Adaptively stacking ensembles for influenza forecasting with incomplete data
• QLSD: Quantised Langevin stochastic dynamics for Bayesian federated learning
• Bregman Divergence Bounds and Universality Properties of the Logarithmic Loss
• Autoregressive Score Matching
• Reduced Perplexity: A simplified perspective on assessing probabilistic forecasts
• Existence and Uniqueness of Proper Scoring Rules
• The Age of Correlated Features in Supervised Learning based Forecasting
• Unified estimation framework for unnormalized models with statistical efficiency
• A Proper Scoring Rule for Validation of Competing Risks Models
• On Deep Neural Network Calibration by Regularization and its Impact on Refinement
• Comparisons of Hyvärinen and pairwise estimators in two simple linear time series models
• Combining Breast Cancer Risk Prediction Models
• Right Decisions from Wrong Predictions: A Mechanism Design Alternative to Individual Calibration