Stability and Sharper Risk Bounds with Convergence Rate $\tilde{O}(1/n^2)$
Bo-Wei Zhu, Shaojie Li, Mingyang Yi, Yong Liu
Renmin University of China Institute of Information Engineering
阅读操作
确认中在文库中上传 PDF 后可生成中文音频讲解。
摘要与影响
Prior work (Klochkov $\&$ Zhivotovskiy, 2021) establishes at most $O\left(\log (n)/n\right)$ excess risk bounds via algorithmic stability for strongly-convex learners with high probability. We show that under the similar common assumptions -- - Polyak-Lojasiewicz condition, smoothness, and Lipschitz continous for losses -- - rates of $O\left(\log^2(n)/n^2\right)$ are at most achievable. To our knowledge, our analysis also provides the tightest high-probability bounds for gradient-based generalization gaps in nonconvex settings.
逐年被引趋势
关键指标
同类平均 = 1
同领域 · 同年份 · 同类型
Google Scholar 与 OpenAlex 的被引统计范围不同,数值存在差异属正常。
AI 辅助阅读
依据:摘要
可就本文提问;依据不足时会说明。
学术脉络
学科主题
计算机 / AIStochastic Gradient Optimization Techniques
Machine Learning and Algorithms · Domain Adaptation and Few-Shot Learning
参考文献 40
此处列出前 3 条
引用本文 2
按被引量排序,此处列出前 3 条