arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1809.01765math.OCcs.LGstat.ML
收藏

有限属性随机稀疏线性回归的样本有效随机梯度迭代保硬方法

Sample Efficient Stochastic Gradient Iterative Hard Thresholding Method for Stochastic Sparse Linear Regression with Limited Attribute Observation

NTT DATA Mathematical Systems Inc.(NTT数据数学系统公司);The University of Tokyo(东京大学);RIKEN(理化学研究所)

Tomoya Murata, Taiji Suzuki

摘要:

我们开发了新的随机梯度法,有效地解决稀疏线性回归在部分属性观察设置,学习者只允许观察固定数量的积极选择的属性每个例子在训练和预测时间。结果表明,该方法在特征值约束条件下的误差为$\varepsilon$时,样本复杂度为$O(1/\varepsilon)$,且与现有方法相比,该速率对问题维数有更好的依赖性.特别地,如果最优解的非零分量的最小值不太小,我们提出的{ \it Hybrid}算法的速度可以提高到接近{ \it full information}算法的minimax最优样本复杂度.其核心思想是:(i)通过迭代使用硬阈值算子来配置探索算法,有效地构造无偏梯度估计器;以及(ii)探索和开发算法的自适应组合,用于快速识别最优的支持,并有效地搜索其支持中的最优参数。实验结果验证了我们的理论研究结果和我们提出的方法的优越性。

英文摘要:

We develop new stochastic gradient methods for efficiently solving sparse linear regression in a partial attribute observation setting, where learners are only allowed to observe a fixed number of actively chosen attributes per example at training and prediction times. It is shown that the methods achieve essentially a sample complexity of $O(1/\varepsilon)$ to attain an error of $\varepsilon$ under a variant of restricted eigenvalue condition, and the rate has better dependency on the problem dimension than existing methods. Particularly, if the smallest magnitude of the non-zero components of the optimal solution is not too small, the rate of our proposed {\it Hybrid} algorithm can be boosted to near the minimax optimal sample complexity of {\it full information} algorithms. The core ideas are (i) efficient construction of an unbiased gradient estimator by the iterative usage of the hard thresholding operator for configuring an exploration algorithm; and (ii) an adaptive combination of the exploration and an exploitation algorithms for quickly identifying the support of the optimum and efficiently searching the optimal parameter in its support. Experimental results are presented to validate our theoretical findings and the superiority of our proposed 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。

↑