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 1111.4470cs.LG
收藏

度量空间中基于近似Lipschitz扩张的有效回归

Efficient Regression in Metric Spaces via Approximate Lipschitz Extension

Ariel University(阿里尔大学);Ben-Gurion University(本-古里安大学);Weizmann Institute of Science(魏茨曼科学研究学院)

Lee-Ad Gottlieb, Aryeh Kontorovich, Robert Krauthgamer

摘要:

我们提出了一个框架,在一般度量空间进行有效的回归。粗略地说,我们的回归器通过计算Lipschitz扩展来预测新点的值-与观察数据一致的最平滑函数-在执行结构风险最小化以避免过拟合之后。我们获得有限样本的风险范围与最小的结构和噪声的假设,和一个自然的速度精度权衡。离线(学习)和在线(预测)阶段可以通过凸规划来解决,但是这种朴素的方法具有运行时复杂性$O(n^3)$,这对于大型数据集是禁止的。相反,我们设计了一个回归算法,其速度和泛化性能取决于该算法适应的数据的内在维度。虽然我们的主要创新是算法,统计结果也可能是独立的利益。

英文摘要:

We present a framework for performing efficient regression in general metric spaces. Roughly speaking, our regressor predicts the value at a new point by computing a Lipschitz extension --- the smoothest function consistent with the observed data --- after performing structural risk minimization to avoid overfitting. We obtain finite-sample risk bounds with minimal structural and noise assumptions, and a natural speed-precision tradeoff. The offline (learning) and online (prediction) stages can be solved by convex programming, but this naive approach has runtime complexity $O(n^3)$, which is prohibitive for large datasets. We design instead a regression algorithm whose speed and generalization performance depend on the intrinsic dimension of the data, to which the algorithm adapts. While our main innovation is algorithmic, the statistical results may also be of independent interest.

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。

↑