Optimal Iterative Sketching with the Subsampled Randomized Hadamard Transform
Optimal Iterative Sketching with the Subsampled Randomized Hadamard Transform
复制标题
使用子采样随机 Hadamard 变换进行最优迭代草图绘制
DOI:
--
复制
发表时间:
2020
期刊:
影响因子:
--
通讯作者:
Mert Pilanci
中科院分区:
文献类型:
--
作者:
Jonathan Lacotte;Sifan Liu;Edgar Dobriban;Mert Pilanci
Random projections or sketching are widely used in many algorithmic and learning contexts. Here we study the performance of iterative Hessian sketch for least-squares problems. By leveraging and extending recent results from random matrix theory on the limiting spectrum of matrices randomly projected with the subsampled randomized Hadamard transform, and truncated Haar matrices, we can study and compare the resulting algorithms to a level of precision that has not been possible before. Our technical contributions include a novel formula for the second moment of the inverse of projected matrices. We also find simple closed-form expressions for asymptotically optimal step-sizes and convergence rates. These show that the convergence rate for Haar and randomized Hadamard matrices are identical, and asymptotically improve upon Gaussian random projections. These techniques may be applied to other algorithms that employ randomized dimension reduction.
DOI:
10.1109/jsait.2020.3039509
发表时间:
2020
期刊:
IEEE Journal on Selected Areas in Information Theory
影响因子:
--
作者:
Sridhar, Srivatsan;Pilanci, Mert;Ozgur, Ayfer
通讯作者:
Ozgur, Ayfer
DOI:
10.1098/rspb.1996.0104
发表时间:
1996-06-22
影响因子:
4.7
作者:
Boomsma, JJ
通讯作者:
Boomsma, JJ
DOI:
--
发表时间:
2020
期刊:
International conference on machine learning
影响因子:
--
作者:
Lacotte, Jonathan;Pilanci, Mert
通讯作者:
Pilanci, Mert