Optimizing a high-dimensional non-convex function is, in general, computationally hard and many problems of this type are hard to solve even approximately. Complexity theory characterizes the optimal approximation ratios achievable in polynomial time in the worst case. On the other hand, when the objective function is random, worst case approximation ratios are overly pessimistic. Mean field spin glasses are canonical families of random energy functions over the discrete hypercube $\{-1,+1\}^N$. The near-optima of these energy landscapes are organized according to an ultrametric tree-like structure, which enjoys a high degree of universality. Recently, a precise connection has begun to emerge between this ultrametric structure and the optimal approximation ratio achievable in polynomial time in the typical case. A new approximate message passing (AMP) algorithm has been proposed that leverages this connection. The asymptotic behavior of this algorithm has been analyzed, conditional on the nature of the solution of a certain variational problem.
In this paper we describe the first implementation of this algorithm and the first numerical solution of the associated variational problem. We test our approach on two prototypical mean-field spin glasses: the Sherrington-Kirkpatrick (SK) model, and the $3$-spin Ising spin glass. We observe that the algorithm works well already at moderate sizes ($N\gtrsim 1000$) and its behavior is consistent with theoretical expectations. For the SK model it asymptotically achieves arbitrarily good approximations of the global optimum. For the $3$-spin model, it achieves a constant approximation ratio that is predicted by the theory, and it appears to beat the `threshold energy' achieved by Glauber dynamics. Finally, we observe numerically that the intermediate states generated by the algorithm have the properties of ancestor states in the ultrametric tree.
Aging Phase Diagram and Exact Asymptotic Energies of Mixed Spherical Spin Glasses
Universität zu Köln(科隆大学);Università di Salerno(萨莱诺大学);CNR-Nanotec, Rome Unit(意大利国家研究委员会纳米技术研究所罗马分部);Sapienza Università di Roma(罗马第一大学);INFN, Sezione di Roma(意大利国家核物理研究所罗马分部)
The algorithmic hardness threshold for continuous random energy models
我们证明了一个算法的硬度结果,找到所谓的\emph{continuous random energy model (CREM)},介绍了Bovier和Kurkova在2004年作为德里达的\emph{generalized random energy model}的扩展的低能量状态。CREM是具有内置分层结构的离散超立方体上的随机能量景观$(X_v)_{v \in \{0,1\}^N}$的模型,并且可以被视为强相关随机能量景观的玩具模型,例如包括Sherrington-Kirkpatrick模型的$p$ -自旋模型家族。CREM由递增函数$A:[0,1]\to[0,1]$参数化,该函数对状态之间的相关性进行编码。我们展示了一个\emph{algorithmic hardness threshold} $x_*$,这是明确的$A$。更确切地说,我们得到两个结果:第一,我们表明,重整化过程结合贪婪搜索产生任何$\varepsilon > 0$的线性时间算法,发现状态$v \in \{0,1\}^N$与$X_v \ge (x_*-\varepsilon) N$。第二,我们表明,值$x_*$基本上是最好的可能性:对于任何$\varepsilon > 0$,任何算法,发现状态$v$与$X_v \ge (x_*+\varepsilon)N$需要指数许多查询的期望和高概率。我们进一步讨论了什么样…
High-dimensional percolation criticality and hints of mean-field-like caging of the random Lorentz gas
随机洛仑兹气体(RLG)是研究无序介质中输运的一种极小模型。尽管该模型具有广泛的相关性,但对其性质的理论把握仍然很薄弱。例如,在空隙逾渗阈值处,其局域化转变的尺寸d的标度在分析上和计算上都没有得到很好的控制。最近一项由玻璃平均场论激发的RLG锁定行为研究[Biroli et al. Phys. Rev. E L030104(2021)]揭示了缩放中的物理不一致性,这增加了对指导的需求。在这里,我们首先扩展分析期望的渐近高D边界上的空隙渗流阈值,然后计算评估的阈值和它的临界性在不同的D。在高-d系统中,我们观察到,标准的渗流物理补充的示踪剂动力学的动力学减速让人想起平均场笼。一个简单的修改的RLG被发现,使渗滤和平均场的笼子之间的相互作用下降到d=3。