高斯信息瓶颈与非微扰重整化群
Gaussian Information Bottleneck and the Non-Perturbative Renormalization Group
摘要:
重整化群(RG)是一类用来解释相互作用多体系统的集体物理的理论技术。有人建议,RG形式主义可能是有用的发现和解释涌现的低维结构在复杂系统的传统物理学背景之外,如在生物学或计算机科学。在这种情况下,一个已经在使用的常见降维框架是信息瓶颈(IB),其中目标是压缩“输入”信号$X$,同时最大化其与一些随机"相关性“变量$Y$的互信息。IB已被应用于脊椎动物和无脊椎动物的处理系统,以表征外部世界的未来运动的最佳编码。其他最近的工作表明,RG计划的二聚体模型可以“发现”的神经网络试图解决一个IB样的问题。本手稿探讨了IB和RG的任何现有制剂在形式上是否等同。一类软截止非微扰RG技术是由非确定粗化映射族定义的,因此可以形式上映射到IB上,反之亦然。为了具体起见,这个讨论完全限于高斯统计(GIB),其中IB有精确的封闭形式的解决方案。在此约束下,GIB具有半群结构,其中连续变换保持IB-最优。此外,可以识别与GIB相关联的RG截止方案。我们的研究结果表明,IB可以用来强加一个概念的“大规模”的结构,如生物功能,RG程序。
英文摘要:
The renormalization group (RG) is a class of theoretical techniques used to explain the collective physics of interacting, many-body systems. It has been suggested that the RG formalism may be useful in finding and interpreting emergent low-dimensional structure in complex systems outside of the traditional physics context, such as in biology or computer science. In such contexts, one common dimensionality-reduction framework already in use is information bottleneck (IB), in which the goal is to compress an ``input'' signal $X$ while maximizing its mutual information with some stochastic ``relevance'' variable $Y$. IB has been applied in the vertebrate and invertebrate processing systems to characterize optimal encoding of the future motion of the external world. Other recent work has shown that the RG scheme for the dimer model could be ``discovered'' by a neural network attempting to solve an IB-like problem. This manuscript explores whether IB and any existing formulation of RG are formally equivalent. A class of soft-cutoff non-perturbative RG techniques are defined by families of non-deterministic coarsening maps, and hence can be formally mapped onto IB, and vice versa. For concreteness, this discussion is limited entirely to Gaussian statistics (GIB), for which IB has exact, closed-form solutions. Under this constraint, GIB has a semigroup structure, in which successive transformations remain IB-optimal. Further, the RG cutoff scheme associated with GIB can be identified. Our results suggest that IB can be used to impose a notion of ``large scale'' structure, such as biological function, on an RG procedure.
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。