Reproduce “Stochastic Langevin Monte Carlo for (weakly) log-concave posterior distributions” 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
Marelys Crespo Navas, Sébastien Gadat, Xavier Gendre
The authors analyze a continuous-time Langevin sampler that switches among uniformly selected observation drifts at exponential times, rather than using the full-data drift. Under smoothness, weak-curvature, prior, minimizer, and initialization conditions with r<1, Theorem 1.1 gives a sufficient horizon for relative entropy J_t to fall below ε. The chosen rate minimizes expected index jumps, not runtime.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.