A Relational Gradient Descent Algorithm For Support Vector Machine Training
A Relational Gradient Descent Algorithm For Support Vector Machine Training
复制标题
支持向量机训练的关系梯度下降算法
DOI:
10.1137/1.9781611976489.8
复制
发表时间:
2021
期刊:
影响因子:
--
通讯作者:
Samadian, A.
中科院分区:
文献类型:
--
作者:
Abo-Khamis, M.;Im, S.;Moseley, B.;Pruhs, K.;Samadian, A.
We consider gradient descent like algorithms for Support Vector Machine (SVM) training when the data is in relational form. For relational data the gradient of the SVM objective cannot be efficiently computed by known techniques as it suffers from the “subtraction problem”. We first show that the subtraction problem cannot be surmounted by showing that computing any constant approximation of the gradient of the SVM objective function is #P-hard, even for acyclic joins. However, we circumvent the subtraction problem by restricting our attention to stable instances, which intuitively are instances where a nearly optimal solution remains nearly optimal if the points are perturbed slightly. We give an efficient algorithm that computes a “pseudo-gradient” that guarantees convergence for stable instances at a rate comparable to that achieved by using the actual gradient. We believe that our results suggest that this sort of stability analysis would likely yield useful insight in the context of designing algorithms on relational data for other learning problems in which the subtraction problem arises.
登录
查看更多内容
DOI:
10.1137/1.9781611976489.7
发表时间:
2021
期刊:
Symposium on Algorithmic Principles of Computer Systems (APOCS
影响因子:
--
作者:
Abo-Khamis, M.;Im, S.;Moseley, B.;Pruhs, K.;Samadian, A.
通讯作者:
Samadian, A.
DOI:
--
发表时间:
2017
期刊:
International Conference on Database Theory
影响因子:
--
作者:
Mahmoud Abo Khamis;H. Ngo;Dan Olteanu;Dan Suciu
通讯作者:
Dan Suciu
DOI:
--
发表时间:
2019-01
期刊:
--
影响因子:
--
作者:
A. Burkov
通讯作者:
A. Burkov
影响因子:
0.9
作者:
Bilu, Yonatan;Linial, Nathan
通讯作者:
Linial, Nathan
影响因子:
22.7
作者:
Roughgarden, Tim
通讯作者:
Roughgarden, Tim