Mercer核的绝对可积性仅对RKHS稳定性具有充分性
Absolute integrability of Mercer kernels is only sufficient for RKHS stability
AI总结:
该研究聚焦连续时间下的Mercer核,证明其绝对可积性仅是再生核希尔伯特空间(RKHS)稳定的充分而非必要条件,完善了RKHS稳定性理论。
摘要:
再生核希尔伯特空间(Reproducing kernel Hilbert spaces,RKHSs)是与被称为核的正定映射一一对应的特殊希尔伯特空间,在机器学习中被广泛用于从稀疏含噪数据中重建未知函数。过去二十年间,一类名为稳定RKHS的子类也被引入线性系统辨识领域。稳定RKHS仅包含正实轴上绝对可积的脉冲响应,因此可作为假设空间,用于从输入输出数据估计线性、时不变且BIBO稳定的动态系统。现有文献已给出RKHS稳定性的充要条件,且已知核的绝对可积性蕴含稳定性。在离散时间框架下,我们在近期工作中证明了后一条件仅具有充分性。本札记的研究目的是证明:在连续时间框架下,该结论对Mercer核同样成立。
英文摘要:
Reproducing kernel Hilbert spaces (RKHSs) are special Hilbert spaces in one-to-one correspondence with positive definite maps called kernels. They are widely employed in machine learning to reconstruct unknown functions from sparse and noisy data. In the last two decades, a subclass known as stable RKHSs has been also introduced in the setting of linear system identification. Stable RKHSs contain only absolutely integrable impulse responses over the positive real line. Hence, they can be adopted as hypothesis spaces to estimate linear, time-invariant and BIBO stable dynamic systems from input-output data. Necessary and sufficient conditions for RKHS stability are available in the literature and it is known that kernel absolute integrability implies stability. Working in discrete-time, in a recent work we have proved that this latter condition is only sufficient. Working in continuous-time, it is the purpose of this note to prove that the same result holds also for Mercer kernels.
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。