arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2502.04282cond-mat.dis-nn
收藏

隔离无相位推断的硬核心:相位选择公式化

Isolating the hard core of phaseless inference: the Phase selection formulation

Davide Straziota, Luca Saglietti

AI总结:

本文提出“相位选择”两层公式化以分离相位恢复中的组合符号恢复与凸回归子任务,利用副本理论刻画自由能景观和相变,并证明结合退火的三种元启发式算法可接近贝叶斯最优样本效率。

摘要:

实值相位恢复是一个非凸连续推断问题,其中需要从一组无符号线性测量数据中重建高维信号。我们聚焦于无噪声情形,旨在厘清相位恢复问题所包含的两个不同子任务:恢复测量缺失符号的困难组合问题,以及回归输入-输出观测以恢复隐藏信号的嵌套凸问题。为此,我们引入并解析刻画了该问题的一个两层公式化形式,称为“相位选择(Phase selection)”。在副本理论(Replica Theory)框架内,我们进行大偏差分析,以刻画在对隐藏符号进行不同猜测时可达到的最小均方误差。此外,我们研究了当两个层次同时优化时问题的自由能景观,并将其作为数据集规模的函数。在低温下,接近贝叶斯最优阈值——该阈值先前已在相位恢复的背景下导出——我们检测到两个自由能分支的共存,一个与随机初始化条件相连,另一个与信号相连。我们推导出一阶相变的相图,在该相变之后两个分支合并。有趣的是,在回归子任务中引入 $L_2$ 正则化可以将相变提前到更小的数据集规模,代价是信号重建中存在偏差,而该偏差可以通过对正则化强度进行退火来消除。最后,我们研究了三种元启发式算法在相位选择背景下的推断性能:模拟退火(Simulated Annealing)、近似消息传递(Approximate Message Passing)以及符号变量连续松弛上的朗之万动力学(Langevin Dynamics)。在温度与 $L_2$ 正则化同时退火的情况下,它们被证明能够接近贝叶斯最优的样本效率。

英文摘要:

Real-valued Phase retrieval is a non-convex continuous inference problem, where a high-dimensional signal is to be reconstructed from a dataset of signless linear measurements. Focusing on the noiseless case, we aim to disentangle the two distinct sub-tasks entailed in the Phase retrieval problem: the hard combinatorial problem of retrieving the missing signs of the measurements, and the nested convex problem of regressing the input-output observations to recover the hidden signal. To this end, we introduce and analytically characterize a two-level formulation of the problem, called ``Phase selection''. Within the Replica Theory framework, we perform a large deviation analysis to characterize the minimum mean squared error achievable with different guesses for the hidden signs. Moreover, we study the free-energy landscape of the problem when both levels are optimized simultaneously, as a function of the dataset size. At low temperatures, in proximity to the Bayes-optimal threshold -- previously derived in the context of Phase retrieval -- we detect the coexistence of two free-energy branches, one connected to the random initialization condition and a second to the signal. We derive the phase diagram for a first-order transition after which the two branches merge. Interestingly, introducing an $L_2$ regularization in the regression sub-task can anticipate the transition to lower dataset sizes, at the cost of a bias in the signal reconstructions which can be removed by annealing the regularization intensity. Finally, we study the inference performance of three meta-heuristics in the context of Phase selection: Simulated Annealing, Approximate Message Passing, and Langevin Dynamics on the continuous relaxation of the sign variables. With simultaneous annealing of the temperature and the $L_2$ regularization, they are shown to approach the Bayes-optimal sample efficiency.

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。

↑