Reproduce “Elliptic Sampling: Optimal Interpolant Schedules for Gaussians and Beyond” 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

Cole Becker, Taylan Kargin, Kimia Hassibi, Asuman Ozdaglar, Pablo A. Parrilo

The authors design sampling paths and numerical solvers together for accuracy under a limited score-evaluation budget. For Gaussian targets, Zoloflow pairs an elliptic schedule with a tailored discretization informed by complex-time trajectory regularity. For exact scores, it achieves Θ(log κ log(√d/ε)) variation query complexity, optimal up to constants among oblivious score-span algorithms; this is a query-count guarantee, not a runtime claim.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.