paper-with-me

홈 › Papers

Geometric Calibration and Neutral Zones for Uncertainty-Aware Multi-Class Classification

2025-11-26 · Soumojit Das, Nairanjana Dasgupta, Prashanta Dutta arxiv

Modern artificial intelligence systems make critical decisions yet often fail silently when uncertain -- even well-calibrated models provide no mechanism to identify \textit{which specific predictions} are unreliable. We develop a geometric framework addressing both calibration and instance-level uncertainty quantification for neural network probability outputs. Treating probability vectors as points on the $(c-1)$-dimensional probability simplex equipped with the Fisher--Rao metric, we construct: (i) Additive Log-Ratio (ALR) calibration maps that reduce exactly to Platt scaling for binary problems while extending naturally to multi-class settings, and (ii) geometric reliability scores that translate calibrated probabilities into actionable uncertainty measures, enabling principled deferral of ambiguous predictions to human review. Theoretical contributions include: consistency of the calibration estimator at rate $O_p(n^{-1/2})$ via M-estimation theory (Theorem~1), and tight concentration bounds for reliability scores with explicit sub-Gaussian parameters enabling sample size calculations for validation set design (Theorem~2). We conjecture Neyman--Pearson optimality of our neutral zone construction based on connections to Bhattacharyya coefficients. Empirical validation on Adeno-Associated Virus classification demonstrates that the two-stage framework captures 72.5\% of errors while deferring 34.5\% of samples, reducing automated decision error rates from 16.8\% to 6.9\%. Notably, calibration alone yields marginal accuracy gains; the operational benefit arises primarily from the reliability scoring mechanism, which applies to any well-calibrated probability output. This work bridges information geometry and statistical learning, offering formal guarantees for uncertainty-aware classification in applications requiring rigorous validation.

📄 PDF Abstract BibTeX arXiv:2511.20960

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-class Classification

Similar Papers 제목 키워드 기반

Calibration Collapse Under Sycophancy Fine-Tuning: How Reward Hacking Breaks Uncertainty Quantification in LLMs

2026-04-12 · Subramanyam Sahoo arxiv

Modern large language models (LLMs) are increasingly fine-tuned via reinforcement learning from human feedback (RLHF) or related reward optimisation schemes. While such procedures improve perceived helpfulness, we invest…

Reinforcement Learning

Uncertainty-Aware Trip Purpose Inference from GPS Trajectories via POI Semantic Zones and Pareto Calibration

2026-05-02 · Bo Yang, Haoxuan Ma, Yifan Liu, Zhiyuan Zhang 외 arxiv

Large-scale GPS trajectory data offer rich observations of human mobility, yet assigning trip purposes to detected stops remains challenging due to the absence of individual-level ground truth, spatial uncertainty from G…

Boundary-Aware Uncertainty Quantification for Wildfire Spread Prediction

2026-05-04 · Jonas V. Funk arxiv

Reliable wildfire spread prediction is vital for risk-aware emergency planning, yet most deep learning models lack principled uncertainty quantification (UQ). Further, for boundary-sensitive cases like wildfire spread, e…

SphUnc: Hyperspherical Uncertainty Decomposition and Causal Identification via Information Geometry

2026-03-01 · Rong Fu, Chunlei Meng, Jinshuo Liu, Dianyu Zhao 외 arxiv

Reliable decision-making in complex multi-agent systems requires calibrated predictions and interpretable uncertainty. We introduce SphUnc, a unified framework combining hyperspherical representation learning with struct…

Representation Learning

A Geometric Method for Improved Uncertainty Estimation in Real-time

2022-06-23 · Gabriella Chouraqui, Liron Cohen, Gil Einziger, Liel Leman

Machine learning classifiers are probabilistic in nature, and thus inevitably involve uncertainty. Predicting the probability of a specific input to be correct is called uncertainty (or confidence) estimation and is cruc…

Management