Reproduce “State Evolution and Universality of Iterated Linear Programs for the Binary Perceptron” 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
Jianan Zhang, Shuangping Li
The authors analyze an iterative programming method for finding sign vectors satisfying random inequalities. Each round optimizes over a cube, freezes coordinates reaching plus or minus one, and lowers the margin. They derive a fixed-round state-evolution recursion for Gaussian and subgaussian matrices. Numerical evaluation reaches the rounding test at density 0.60, but does not certify a threshold.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.