AI 中文总结
针对随机矩阵偏差问题,提出近似消息传递迭代算法,在自由概率框架下建立状态演化,实现算子范数 $2\sigma(\alpha)$,解决 Kunisky-Zhang 和 Maillard 的算法问题。
AI 中文摘要
设 $A_1,\ldots,A_n$ 为独立的 $d \times d$ 实对称高斯随机矩阵,并考虑线性算子 $A(x) = n^{-1/2}\sum_{i=1}^n x_i A_i$,其中 $x\in \mathbb{R}^n$。我们在近似消息传递(Approximate Message Passing)框架中构造了一个迭代算法,该算法在 $A$ 及其伴随算子 $A^*$ 上迭代,并建立了状态演化(state evolution)结果,在 $d\rightarrow \infty, 2n/d^2 \rightarrow \alpha$ 的极限下,以自由概率空间中的相关高斯-半圆过程(correlated Gaussian-semicircular process)刻画其行为,此处收敛性为算子的强收敛。随后,我们将该迭代应用于随机矩阵偏差问题,该问题要求寻找一个二元向量 $x \in \{-1,+1\}^n$ 使得 $A(x)$ 具有较小的算子范数。我们的算法实现了算子范数 $2\sigma(\alpha)$,其中标准差 $\sigma(\alpha)<1$ 对所有 $0<\alpha<\alpha_* \simeq 5.74$ 有显式表达式。这解决了 Kunisky-Zhang (2023) 和 Maillard (2025) 在该区间内的算法问题。
英文摘要
Let $A_1,\ldots,A_n$ be independent $d \times d$ real symmetric Gaussian random matrices, and consider the linear operator $A(x) = n^{-1/2}\sum_{i=1}^n x_i A_i$, $x\in \mathbb{R}^n$. We construct an iterative algorithm in the Approximate Message Passing family which iterates over $A$ and its adjoint $A^*$, and establish a state evolution result which characterizes its behavior in the limit $d\rightarrow \infty, 2n/d^2 \rightarrow α$ in terms of a correlated Gaussian-semicircular process in a free probability space, in the sense of strong convergence of operators. We then apply this iteration to the random matrix discrepancy problem which asks for a binary vector $x \in \{-1,+1\}^n$ such that $A(x)$ has a small operator norm. Our algorithm achieves an operator norm $2σ(α)$, for an explicit expression of the standard deviation $σ(α)<1$ for all $0<α<α_* \simeq 5.74$. This resolves the algorithmic question of Kunisky-Zhang (2023) and Maillard (2025) in this interval.