arXiv Machine Learning

Refinement as a Service: Algorithmic Predictor Refinement

The paper investigates how to combine multiple calibrated predictors into a single refined predictor that preserves all available information and cannot be further refined. It models calibrated predictors as signaling schemes and defines refinement via feature‑independent garblings, showing that a new predictor is constructible exactly when its signal vector lies in the linear span of the input signal vectors. The authors provide algorithmic results: deterministic refinement is polynomial‑time solvable for two predictors but NP‑hard for many, while randomized refinement admits a polynomial‑time algorithm for any number of inputs by decomposing signal vectors into extreme rays of a polyhedral cone.

arXiv AI

Sep 10

How to Verify Probabilistic Consistency of Predictive Models

The paper presents an interactive probabilistically checkable proof (PCP) protocol that allows a polynomial‑time verifier to check the approximate consistency of a probabilistic predictor defined by two circuits, P and Q. By evaluating these circuits at a few points and querying a proof oracle that encodes a witnessing probability distribution, the verifier can confirm that the predictor’s many conditional‑probability claims are self‑consistent. The authors also establish that the problem of verifying l₂‑approximate consistency for explicit probabilistic claims lies in NP, with certificates of size O(mn + log B), and show how to eliminate dependence on the input bit‑precision B through a small additive gap.

By Orr Paradise, Oliver Richardson, Yoshua Bengio, Shafi Goldwasser

safety

arXiv AI

4d ago

Predictive Closure: A Set-Level Characterization of JEPA's Feature Selection

arXiv:2610.27364v1 Announce Type: cross Abstract: In joint-embedding predictive architectures (JEPA), an encoder and a predictor are trained together to produce a representation that minimizes the er...

By Mosh Levy, Aly Lidayan, Yoav Goldberg

rag

arXiv AI

Aug 12

How to Verify Consistency of Probabilistic Claims

arXiv:2608. 11181v1 Announce Type: cross Abstract: When a probabilistic predictor answers many conditional-probability queries, are its answers self-consistent, and can this be verified in polynomial time?

By Orr Paradise, Oliver Richardson, Yoshua Bengio, Shafi Goldwasser

safety

arXiv Machine Learning

Jul 23

Optimal Recalibration of an Online Predictor

arXiv:2607. 19689v1 Announce Type: cross Abstract: We study the problem of recalibrating an online predictor [KE17, OKS24]: given an arbitrary "hint" sequence of forecasts, the learner must output new predictions that are calibrated while incurring small excess error relative to the original forecasts, under a proper loss.

By Lunjia Hu, Kevin Tian, Chutong Yang

arXiv Machine Learning

Jun 9

Optimal and Provable Calibration in High-Dimensional Binary Classification: Angular Calibration and Platt Scaling

arXiv:2502. 15131v4 Announce Type: replace-cross Abstract: We study the fundamental problem of calibrating a linear binary classifier of the form $\sigma(\hat{w}^\top x)$, where the feature vector $x$ is Gaussian, $\sigma$ is a link function, and $\hat{w}$ is an estimator of the true linear weight $w^\star$.

By Yufan Li, Pragya Sur

arXiv Machine Learning

Oct 16

Computational and Statistical Hardness of Calibration Distance

The paper investigates the computational and statistical challenges of the calibration distance, a key metric for measuring miscalibration in probabilistic predictors. It presents an efficient algorithm for exact computation when the distribution has a uniform marginal and noiseless labels, and shows that the problem becomes NP‑hard if either assumption is dropped. The authors also provide a polynomial‑time approximation scheme for the general case and establish tight sample complexity bounds for estimating the calibration distance from data.

By Mingda Qiao

arXiv Statistics ML

Oct 7

Concentration and Calibration in Predictive Bayesian Inference

arXiv:2605.00455v2 Announce Type: replace-cross Abstract: Predictive Bayesian inference (PBI) represents a model-and prior-agnostic approach to standard Bayesian inference which allows users to quant...

By David T. Frazier, Hui Wang

arXiv Machine Learning

Sep 1

On the Complexity of the Compatibility Problem for Succinctly Encoded Conditional Distributions

arXiv:2608.31120v1 Announce Type: new Abstract: The motivation for this paper is the investigation of the trade-offs implicit in probabilistic models used in machine learning. Models are often used t...

By Guy Emerson

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...

By Xuelin Yang, Baihe Huang, Yilong Hou, Guido Imbens, Michael I. Jordan

arXiv AI

Oct 7

Complementary Feature Domains: Information Preservation Does Not Imply Predictive-Contribution Preservation

arXiv:2610.07565v1 Announce Type: cross Abstract: Complementary Feature Domains (CFD) theory characterizes predictive value as a context-indexed contribution system induced jointly by representations...

By Timothy Oladunni, Farouk Ganiyu-Adewumi

arXiv Machine Learning

Jun 3

Hierarchies of Calibration: Classification meets Regression

arXiv:2606. 03245v1 Announce Type: cross Abstract: Concepts of calibration formalize the compatibility between probabilistic predictions and the respective outcomes.

By Johannes Resin, Lu Yang, Tilmann Gneiting

arXiv AI

Jun 4

Bayes-Sufficient Representations in Supervised Learning

arXiv:2606. 04045v1 Announce Type: cross Abstract: Representation learning is often described as preserving the information in an input that is relevant for prediction.

By Vasileios Sevetlidis

Related stories