arXiv：cs.LG· Jon Sporring·· 4 小时前
从人类修正到学习式分割：信息、学习与人力投入的批判性数学综述
From Human Corrections to Learned Segmentations: A Critical Mathematical Review of Information, Learning, and Human Effort
AI 导读
一篇 40 页的批判性综述用统一数学框架追踪反馈的选择、学习器更新与评估三个环节，比较主动学习、机器教学、交互式分割与序贯预测评估。精确贝叶斯更新将评估标签信息转化为期望对数损失改善，超额风险分解解释近似学习器损失，条件信息分解区分所选位置、标签与展示上下文的作用。作者明确不提出新采集算法，也不主张经验优越性。
正文
Abstract:When does a human correction become useful learning, and what establishes better segmentation at matched human effort? This critical narrative review follows feedback through its selection, learner update, and evaluation. It compares active learning, machine teaching, interactive segmentation, and sequential predictive evaluation using a common mathematical account of target information, predictive error, response predictability, and human work. An exact Bayesian update converts evaluation-label information into expected log-loss improvement; an excess-risk decomposition explains what an approximate learner can lose. Conditional information decompositions separate the roles of selected locations, labels, and displayed context. Empirical comparisons show why response protocols, update mechanisms, and effort denominators matter, distinguishing current-mask refinement from reusable learning and simulated interaction from human evidence. We identify what logs can reveal, what requires independent evaluation, and what remains model-dependent. The resulting research priorities are to test what selection reveals, whether using it improves assimilation, and whether the resulting interaction policy benefits segmentation at matched effort. These are distinct claims: predicting a teacher's responses need not identify human intentions or establish better learning. No new acquisition algorithm or empirical superiority is claimed.
| Comments: | 40 pages, literature-selection and search record included |
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.20396 [cs.LG] |
| (or arXiv:2610.20396v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.20396 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jon Sporring [view email]
[v1]
Wed, 14 Oct 2026 16:00:20 UTC (60 KB)
来源：arXiv：cs.LG · arxiv.org