arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1701.06607stat.ML
收藏

从随机正弦特征图中稳定恢复稀疏向量

Stable Recovery Of Sparse Vectors From Random Sinusoidal Feature Maps

Mohammadreza Soltani, Chinmay Hegde

摘要:

随机正弦特征是在大型数据集中加速基于核的推理的流行方法。在推理阶段之前,该方法建议通过首先将每个数据向量乘以随机高斯矩阵来执行降维,然后计算逐元素正弦曲线。理论分析表明,收集足够数量的这样的特征可以可靠地用于核分类和回归的后续推理。在这项工作中,我们证明,随着嵌入维数的轻微增加,也可以从这种随机正弦特征中重建数据向量,前提是底层数据足够稀疏。特别是,我们提出了一个数值稳定的算法重建给定的非线性特征的数据向量,并分析其样本的复杂性。我们的算法可以扩展到其他类型的结构化反问题,如分离一对稀疏(但不相干)的向量。我们通过数值实验支持我们的方法的有效性。

英文摘要:

Random sinusoidal features are a popular approach for speeding up kernel-based inference in large datasets. Prior to the inference stage, the approach suggests performing dimensionality reduction by first multiplying each data vector by a random Gaussian matrix, and then computing an element-wise sinusoid. Theoretical analysis shows that collecting a sufficient number of such features can be reliably used for subsequent inference in kernel classification and regression. In this work, we demonstrate that with a mild increase in the dimension of the embedding, it is also possible to reconstruct the data vector from such random sinusoidal features, provided that the underlying data is sparse enough. In particular, we propose a numerically stable algorithm for reconstructing the data vector given the nonlinear features, and analyze its sample complexity. Our algorithm can be extended to other types of structured inverse problems, such as demixing a pair of sparse (but incoherent) vectors. We support the efficacy of our approach via numerical experiments.

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。

↑