更快的主成分回归与稳定的矩阵切比雪夫逼近
Faster Principal Component Regression and Stable Matrix Chebyshev Approximation
AI总结:
本文提出了一种通过减少黑盒调用次数来实现主成分回归的算法,其精度为1+γ,且无需显式构造主成分,适用于大规模数据。同时,开发了稳定的矩阵切比雪夫多项式递推公式和最优多项式逼近矩阵符号函数的方法。
摘要:
我们通过将问题转化为至多$\tilde{O}(γ^{-1})$次黑盒调用的岭回归来解决主成分回归(PCR),从而在乘法精度$1+γ$内达到目标。因此,我们的算法不需要显式构造顶部主成分,适用于大规模PCR实例。相比之下,先前结果需要$\tilde{O}(γ^{-2})$次这样的黑盒调用。我们通过开发一个通用的稳定递推公式用于矩阵切比雪夫多项式,以及一个最优次数的多项式逼近矩阵符号函数来获得这一结果。我们的技术可能具有独立的兴趣,尤其是在设计迭代方法时。
英文摘要:
We solve principal component regression (PCR), up to a multiplicative accuracy $1+γ$, by reducing the problem to $\tilde{O}(γ^{-1})$ black-box calls of ridge regression. Therefore, our algorithm does not require any explicit construction of the top principal components, and is suitable for large-scale PCR instances. In contrast, previous result requires $\tilde{O}(γ^{-2})$ such black-box calls. We obtain this result by developing a general stable recurrence formula for matrix Chebyshev polynomials, and a degree-optimal polynomial approximation to the matrix sign function. Our techniques may be of independent interests, especially when designing iterative methods.
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。