Stability Analysis and Learning Bounds for Transductive Regression Algorithms
- Google Research（谷歌研究院）
- Courant Institute of Mathematical Sciences（库朗数学科学研究所）
- NEC Laboratories America（NEC美国实验室）
- Technion - Israel Institute of Technology（以色列理工学院）
机构由 AI 辅助整理，请以论文原文为准。
更新
英文摘要：
This paper uses the notion of algorithmic stability to derive novel generalization bounds for several families of transductive regression algorithms, both by using convexity and closed-form solutions. Our analysis helps compare the stability of these algorithms. It also shows that a number of widely used transductive regression algorithms are in fact unstable. Finally, it reports the results of experiments with local transductive regression demonstrating the benefit of our stability bounds for model selection, for one of the algorithms, in particular for determining the radius of the local neighborhood used by the algorithm.
