Fundamental limits of Non-Linear Low-Rank Matrix Estimation
arxiv(2024)
摘要
We consider the task of estimating a low-rank matrix from non-linear and
noisy observations. We prove a strong universality result showing that
Bayes-optimal performances are characterized by an equivalent Gaussian model
with an effective prior, whose parameters are entirely determined by an
expansion of the non-linear function. In particular, we show that to
reconstruct the signal accurately, one requires a signal-to-noise ratio growing
as N^1/2 (1-1/k_F), where k_F is the first non-zero Fisher
information coefficient of the function. We provide asymptotic characterization
for the minimal achievable mean squared error (MMSE) and an approximate
message-passing algorithm that reaches the MMSE under conditions analogous to
the linear version of the problem. We also provide asymptotic errors achieved
by methods such as principal component analysis combined with Bayesian
denoising, and compare them with Bayes-optimal MMSE.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要