arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2004.08454cs.CCcs.DSstat.ML
收藏

低次猜想的反例

Counterexamples to the Low-Degree Conjecture

Justin Holmgren, Alexander S. Wein

摘要:

Hopkins(2018)的一个猜想假设,对于某些高维假设检验问题,没有多项式时间算法可以优于所谓的“简单统计”,这是数据中的低次多项式。这一猜想形式化了围绕最近一系列工作的信念,这些工作试图通过低度似然比来理解计算与计算的权衡。在这项工作中,我们反驳了霍普金斯的猜想。然而,我们的反例至关重要地利用了猜想中使用的噪声算子的细节,我们指出了一个简单的方法来修改猜想,以排除我们的反例。我们还给出了一个例子,说明(即使经过上述修改),在猜想中的对称性假设是必要的。这些结果并没有破坏计算下限的低度框架,而是旨在更好地理解它适用于哪类问题。

英文摘要:

A conjecture of Hopkins (2018) posits that for certain high-dimensional hypothesis testing problems, no polynomial-time algorithm can outperform so-called "simple statistics", which are low-degree polynomials in the data. This conjecture formalizes the beliefs surrounding a line of recent work that seeks to understand statistical-versus-computational tradeoffs via the low-degree likelihood ratio. In this work, we refute the conjecture of Hopkins. However, our counterexample crucially exploits the specifics of the noise operator used in the conjecture, and we point out a simple way to modify the conjecture to rule out our counterexample. We also give an example illustrating that (even after the above modification), the symmetry assumption in the conjecture is necessary. These results do not undermine the low-degree framework for computational lower bounds, but rather aim to better understand what class of problems it is applicable to.

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。

↑