arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.15589cs.DScs.LG
收藏

有效的张量分解

Efficient Tensor Decomposition

Northwestern University(西北大学)

Aravindan Vijayaraghavan

摘要:

本章研究将一个张量分解为一个组成秩为1的张量之和的问题。虽然张量分解在设计学习算法和数据分析中非常有用,但它们在最坏情况下是NP困难的。我们将看到如何在温和的假设下设计具有可证明保证的有效算法,并使用超越最坏情况的框架,如平滑分析。

英文摘要:

This chapter studies the problem of decomposing a tensor into a sum of constituent rank one tensors. While tensor decompositions are very useful in designing learning algorithms and data analysis, they are NP-hard in the worst-case. We will see how to design efficient algorithms with provable guarantees under mild assumptions, and using beyond worst-case frameworks like smoothed analysis.

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。

↑