arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1002.2044cs.LG
收藏

存在多个风险最小化时经验风险最小化的稳定性

On the Stability of Empirical Risk Minimization in the Presence of Multiple Risk Minimizers

Benjamin I. P. Rubinstein, Aleksandr Simma

摘要:

最近,Kespero和Niyogi研究了算法稳定性的几个概念-学习映射的一个属性,在概念上类似于连续性-表明训练稳定性足以保证经验风险最小化的一致性,而无分布CV稳定性对于具有有限VC维度是必要和充分的。本文关注的是由同一作者提出的ERM训练稳定性的一个相变。Kendall和Niyogi证明了有限假设空间中包含唯一风险最小化的ERM具有随样本大小呈指数级变化的训练稳定性,并证明了多个风险最小化的存在甚至阻止了超二次收敛。我们证明了这一结果的严格较弱的概念CV稳定性,积极解决的猜想。

英文摘要:

Recently Kutin and Niyogi investigated several notions of algorithmic stability--a property of a learning map conceptually similar to continuity--showing that training-stability is sufficient for consistency of Empirical Risk Minimization while distribution-free CV-stability is necessary and sufficient for having finite VC-dimension. This paper concerns a phase transition in the training stability of ERM, conjectured by the same authors. Kutin and Niyogi proved that ERM on finite hypothesis spaces containing a unique risk minimizer has training stability that scales exponentially with sample size, and conjectured that the existence of multiple risk minimizers prevents even super-quadratic convergence. We prove this result for the strictly weaker notion of CV-stability, positively resolving the conjecture.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑