arXiv Machine Learning
Bayes with No Shame: Admissibility Geometries of Predictive Inference
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Jun 10
WorldKernel: A World Model is the Coupling Kernel of Admissible Possible Worlds
arXiv:2606. 10934v1 Announce Type: new Abstract: A common assumption holds that enough observational and interventional data, given to a strong enough predictor, suffices.
arXiv Machine Learning
Jul 3
Prediction Sets for Counterfactual Decisions: Coverage, Optimality, and Conformal Prediction
arXiv:2607. 02206v1 Announce Type: cross Abstract: Predictions are increasingly used to guide high-stakes decisions, from treatment selection to policy making.
arXiv Machine Learning
Jun 8
Predictable Compression Failures: Order Sensitivity and Information Budgeting for Evidence-Grounded Binary Adjudication
arXiv:2509. 11208v3 Announce Type: replace-cross Abstract: Transformers used for evidence-grounded binary adjudication (e.
arXiv Machine Learning
Sep 23
PICPIs: Prediction-Interval-Conditional Prediction Intervals
arXiv:2609.25388v1 Announce Type: cross Abstract: A classical question in statistics is which observable quantities to condition on when drawing inferences about unobservable targets. For conformal p...
arXiv Machine Learning
Jun 9
A Joint Finite-Sample Certificate for Adaptive Selective Conformal Risk Control
arXiv:2606. 08517v1 Announce Type: new Abstract: Selective predictors answer on confident inputs and abstain elsewhere; deploying one safely needs a single finite-sample certificate that simultaneously upper-bounds the selected risk, lower-bounds the acceptance probability $\pacc$ above a floor $\pmin$, and lower-bounds the deployment utility.
arXiv Machine Learning
Jun 24
LLMs are Bayesian, In Expectation, Not in Realization
arXiv:2507. 11768v3 Announce Type: replace-cross Abstract: Bayesian accounts of in-context learning face a direct objection: exact posterior predictives for exchangeable data are invariant to task-preserving order, yet transformers change next-token probabilities when the same examples are serialized differently.