Reproduce “Statistical Physics of Signal Estimation in Gaussian Noise: Theory and Examples of Phase Transitions” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Neri Merhav, Dongning Guo, Shlomo Shamai
The authors use statistical-physics methods with the I–MMSE relation to analyze denoising in Gaussian noise. They represent posterior weights with a partition function and use it to derive estimation error. For a random spherical codebook, asymptotic MMSE per coordinate changes at the capacity threshold: it matches Gaussian-input MMSE below, and is zero at or above; this is not a finite-length result.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.