Pandora's Regret is a closed-form pairwise scoring rule derived from expected optimal search costs that elicits true probabilities and outperforms log loss, accuracy, and F1 at predicting diagnostic costs on MedMNIST models.
Verifying probabilistic forecasts: Calibration and sharpness
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 1
other 1
citation-polarity summary
representative citing papers
Stochastic Attention adds calibrated uncertainty to transformer foundation models through inference-time multinomial sampling of attention weights and univariate post-hoc tuning of a concentration parameter.
Finite ensemble sizes cause systematic slope attenuation in conditional reliability diagnostics for means, spreads, and probabilities; analytical expressions and practical estimators correct for this bias.
Proposes adaptive multiple importance sampling for robust Bayesian model evidence estimation under parameter non-identifiability, shown to outperform deterministic methods on ecological case studies while being cheaper than MCMC.
Embedding selection mechanisms into generative simulators enables amortized Bayesian inference to produce debiased, well-calibrated posteriors without tractable likelihoods.
Zero-shot TSFMs conditioned on leakage-safe covariates from Google Trends and an institutional index forecast commencing enrolments competitively with classical methods under data sparsity.
EnScale emulates high-resolution regional climate model outputs from global circulation models for multiple variables using a two-step generative process with sparse local stochastic layers and energy score optimization, including a temporally consistent variant.
A new error-damping estimator for compositional score matching enables stable amortized inference on hierarchical Bayesian models with over 750,000 parameters using fewer than one full model simulation on large problems.
rcosmo is an R package offering functions to convert and analyze geographic, point pattern, and star-shaped spherical data in HEALPix format with ready-to-use code examples.
citing papers explorer
-
Pandora's Regret: A Proper Scoring Rule for Evaluating Sequential Search
Pandora's Regret is a closed-form pairwise scoring rule derived from expected optimal search costs that elicits true probabilities and outperforms log loss, accuracy, and F1 at predicting diagnostic costs on MedMNIST models.
-
Calibrating Scientific Foundation Models with Inference-Time Stochastic Attention
Stochastic Attention adds calibrated uncertainty to transformer foundation models through inference-time multinomial sampling of attention weights and univariate post-hoc tuning of a concentration parameter.
-
Ensemble size effects on conditional reliability estimates: slope attenuation bias and correction methods
Finite ensemble sizes cause systematic slope attenuation in conditional reliability diagnostics for means, spreads, and probabilities; analytical expressions and practical estimators correct for this bias.
-
Reliable model selection in the presence of parameter non-identifiability
Proposes adaptive multiple importance sampling for robust Bayesian model evidence estimation under parameter non-identifiability, shown to outperform deterministic methods on ecological case studies while being cheaper than MCMC.
-
Overcoming Selection Bias in Statistical Studies With Amortized Bayesian Inference
Embedding selection mechanisms into generative simulators enables amortized Bayesian inference to produce debiased, well-calibrated posteriors without tractable likelihoods.
-
Forecasting Commencing Enrolments Under Data Sparsity: A Zero-Shot Time Series Foundation Models Framework for Higher Education Planning
Zero-shot TSFMs conditioned on leakage-safe covariates from Google Trends and an institutional index forecast commencing enrolments competitively with classical methods under data sparsity.
-
EnScale: Temporally-consistent multivariate generative downscaling via proper scoring rules
EnScale emulates high-resolution regional climate model outputs from global circulation models for multiple variables using a two-step generative process with sparse local stochastic layers and energy score optimization, including a temporally consistent variant.
-
Compositional amortized inference for large-scale hierarchical Bayesian models
A new error-damping estimator for compositional score matching enables stable amortized inference on hierarchical Bayesian models with over 750,000 parameters using fewer than one full model simulation on large problems.
-
Spherical data handling and analysis with R package rcosmo
rcosmo is an R package offering functions to convert and analyze geographic, point pattern, and star-shaped spherical data in HEALPix format with ready-to-use code examples.