arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2311.07540cs.DSmath.PRmath.STstat.TH
收藏

使用梯度下降寻找植入团

Finding planted cliques using gradient descent

Reza Gheissari, Aukosh Jagannath, Yiming Xu

AI总结:

针对植入团恢复中黑箱优化缺乏保证的问题,本文用 Lagrange 乘子将团约束纳入 Hamiltonian,证明从完整图初始化的梯度下降及其低温松弛可在 k=Ω(√n) 时恢复植入团,并验证污染鲁棒性。

摘要:

植入团问题是统计到计算鸿沟的一个范式模型:当植入团大小满足 k≥2 log₂n 时,它在信息论意义上可被检测;但对于恢复任务,只有当 k=Ω(√n) 时才存在多项式时间算法。到目前为止,已有许多算法在 k=Ω(√n) 时即可成功。然而引人注目的是,尚无黑箱优化方法(例如梯度下降或 Metropolis 过程)被证明有效。事实上,Chen、Mossel 和 Zadik 最近证明,任何以团集合为状态空间的 Metropolis 过程,如果自然地从空集初始化,都无法在多项式时间内找到任何亚线性大小的植入团。我们证明,使用 Lagrange 乘子法,即在所有子图构成的空间上优化由目标函数与团约束之和给出的 Hamiltonian,能够取得成功。具体而言,我们证明,使该 Hamiltonian 最小化的 Markov 链(梯度下降及其低温松弛)若从完整图初始化,便能成功恢复大小为 k=Ω(√n) 的植入团。重要的是,若从空集初始化,该松弛仍无法帮助梯度下降找到亚线性植入团。我们还在一种自然污染模型下展示了这些 Markov 链方法的鲁棒性。

英文摘要:

The planted clique problem is a paradigmatic model of statistical-to-computational gaps: the planted clique is information-theoretically detectable if its size $k\ge 2\log_2 n$ but polynomial-time algorithms only exist for the recovery task when $k= Ω(\sqrt{n})$. By now, there are many algorithms that succeed as soon as $k = Ω(\sqrt{n})$. Glaringly, however, no black-box optimization method, e.g., gradient descent or the Metropolis process, has been shown to work. In fact, Chen, Mossel, and Zadik recently showed that any Metropolis process whose state space is the set of cliques fails to find any sub-linear sized planted clique in polynomial time if initialized naturally from the empty set. We show that using the method of Lagrange multipliers, namely optimizing the Hamiltonian given by the sum of the objective function and the clique constraint over the space of all subgraphs, succeeds. In particular, we prove that Markov chains which minimize this Hamiltonian (gradient descent and a low-temperature relaxation of it) succeed at recovering planted cliques of size $k = Ω(\sqrt{n})$ if initialized from the full graph. Importantly, initialized from the empty set, the relaxation still does not help the gradient descent find sub-linear planted cliques. We also demonstrate robustness of these Markov chain approaches under a natural contamination model.

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。

↑