高维聚类中的计算—信息差距
Computation-information gap in high-dimensional clustering
AI总结:
本文研究高维各向同性高斯混合聚类的计算—信息差距,证明低次多项式计算壁垒并表明信息壁垒更低,从而为 $p\geq n$ 时差距普遍存在提供证据。
摘要:
我们研究在环境维度 $p$ 大于样本点数量 $n$ 的高维情形下,对各向同性高斯混合模型进行聚类时,是否存在根本性的计算—信息差距。arXiv:1610.02918 基于统计物理学中的复本启发式方法,推测在特定的贝叶斯高维渐近情形中存在计算—信息差距。我们通过以下两方面为这种差距在 $p \geq n$ 的高维情形中普遍存在提供证据:(i)证明了高维聚类的非渐近低次多项式计算壁垒,并与已知最优多项式时间算法的性能相匹配;(ii)证明当聚类数 $K$ 足够大时,聚类的信息壁垒小于计算壁垒。这些结果与(适度)低维情形 $n \geq poly(p,K)$ 形成对比,在该情形下对各向同性高斯混合模型进行聚类不存在计算—信息差距。为证明我们的低次计算壁垒,我们发展了精细的组合论证,以在 Bernoulli 贝叶斯模型下对信号的混合矩给出上界。
英文摘要:
We investigate the existence of a fundamental computation-information gap for the problem of clustering a mixture of isotropic Gaussian in the high-dimensional regime, where the ambient dimension $p$ is larger than the number $n$ of points. The existence of a computation-information gap in a specific Bayesian high-dimensional asymptotic regime has been conjectured by arXiv:1610.02918 based on the replica heuristic from statistical physics. We provide evidence of the existence of such a gap generically in the high-dimensional regime $p \geq n$, by (i) proving a non-asymptotic low-degree polynomials computational barrier for clustering in high-dimension, matching the performance of the best known polynomial time algorithms, and by (ii) establishing that the information barrier for clustering is smaller than the computational barrier, when the number $K$ of clusters is large enough. These results are in contrast with the (moderately) low-dimensional regime $n \geq poly(p, K)$, where there is no computation-information gap for clustering a mixture of isotropic Gaussian. In order to prove our low-degree computational barrier, we develop sophisticated combinatorial arguments to upper-bound the mixed moments of the signal under a Bernoulli Bayesian 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。