arXiv cs.AI· Christopher J. Hazard, Michael Resnick, Jacob Beel, Jack Xia, Cade Mack, Dominic Glennie, Matthew Fulp, David Maze, Andrew Bassett, Martin Koistinen·· 6 天前AI 评分23
一种信息力学理论：通过测量不确定性实现泛化（学习即测量）
A Theory of the Mechanics of Information: Generalization Through Measurement of Uncertainty (Learning is Measuring)
AI 导读
研究者提出一种"无模型"的基于实例学习框架，用信息论中的惊奇度（surprisal）直接分析原始数据并做推理，无需建模数据分布，并支持直接编辑和删除训练数据。该方法可泛化到生成式推理、因果发现、异常检测和时间序列预测等任务，在异常检测和部分监督任务上达到 SOTA，并能处理缺失数据。论文称其数学基础构建了一套信息的"物理学"，为可扩展且人类可理解的机器学习提供了可能。
正文 · 原文
Abstract:Traditional machine learning relies on explicit models and domain assumptions, often limiting flexibility and interpretability. We introduce a "model-free" framework of instance-based learning using surprisal (information theoretic uncertainty) to directly analyze and perform inferences from raw data, eliminating distribution modeling, reducing bias, and enabling efficient updates including direct edits and deletion of training data. By quantifying relevance through uncertainty, the approach enables generalizable inference across tasks including generative inference, causal discovery, anomaly detection, and time series forecasting. Our approach emphasizes traceability, interpretability, and data-driven decision making, offering a unified, human-understandable framework for machine learning, can be adapted to virtually all machine learning tasks, achieving competency across all and state-of-the-art performance on anomaly detection and some supervised tasks. The mathematical foundations create a "physics" of information, which enable these techniques to apply effectively to a wide variety of complex data types, including missing data. Our results suggest that this may be a viable foundation upon which to build scalable machine learning and artificial intelligence that can maintain human understandability of the underlying mechanics.
| Comments: | 119 pages |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Statistics Theory (math.ST); Machine Learning (stat.ML) |
| Cite as: | arXiv:2510.22809 [cs.LG] |
| (or arXiv:2510.22809v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2510.22809 arXiv-issued DOI via DataCite |
Submission history
From: Christopher Hazard [view email]
[v1]
Sun, 26 Oct 2025 19:45:25 UTC (2,789 KB)
[v2]
Thu, 8 Oct 2026 19:07:29 UTC (2,781 KB)
来源：arXiv cs.AI · arxiv.org