stat.MLNov 13, 2026

Elliptic Sampling: Optimal Interpolant Schedules for Gaussians and Beyond

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

Organizations: Laboratory for Information and Decision Systems (LIDS), Massachusetts Institute of Technology

Abstract

Generative modeling based on stochastic interpolants requires specifying two key choices: an interpolant schedule bridging the initial and target distributions, and an efficient discretization of the resulting probability-flow ODE. In this work, we introduce a new framework for joint schedule/discretization design based on the analyticity properties of the (complexified) ODE trajectories, which in turn ensure good numerical behavior. Our formulation can be solved exactly via conformal mapping, yielding a natural family of variance-preserving elliptic schedules, parametrized by Jacobi elliptic functions. Pairing an elliptic schedule with a tailored discretization, we obtain Zoloflow, a new sampling algorithm closely connected to Zolotarev's optimal rational function approximants. Crucially, both the elliptic schedule and Zoloflow explicitly incorporate the condition number κκ of the target distribution and reduce to the classical trig schedule in the limit κ→1κ\rightarrow 1. For Gaussian targets, Zoloflow achieves minimax optimality among all oblivious score-span algorithms, attaining total-variation error ε\varepsilon using Θ(log⁡κ log⁡(d/ε))Θ(\logκ\,\log(\sqrt d/\varepsilon)) (exact) score queries. For the log-concave case, the elliptic schedule allows sampling with at most ε\varepsilon 2-Wasserstein-error by requiring merely O~(d polylog(κ,1/ε))\widetilde{O}(\sqrt{d} \, \mathrm{polylog}(κ, 1/\varepsilon)) score evaluations. Complementing these theoretical results, we empirically evaluate the elliptic schedule on general (non-log-concave) target distributions, including detailed comparisons with alternative schedule proposals on both synthetic benchmarks and existing image generation datasets.

Figures & tables

Appendix figures & tables27 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Sep 22, 2026

Gaussian Flow-Matching Schedules: Implications for Sampling and Training

Flow-matching schedules affect both sampling dynamics and the variance of the regression target. For centered commuting Gaussians, we show that a direction-dependent schedule decomposes into two independent design choices: a variance path, which fully determines the intermediate laws and probability flow, and a factorization, which leaves this flow unchanged while controlling irreducible regression variance. On the sampling side, we analyze finite-step Euler accuracy and derive a necessary drift bound for exact N -step sampling, connecting the geodesic and the logarithmic path. On the training side, for any fixed path, we derive closed-form factorizations that either minimize time-averaged regression variance or make it constant along the path.
Sep 30, 2026

Correcting CondOT: Exact Finite-Step Sampling in Gaussian Flow Matching

Flow matching generates samples by gradually transforming noise into data. In practice, using a finite number of sampling steps introduces a numerical error that depends on the chosen schedule. We study this dependence for Gaussian targets and the explicit midpoint sampling method, using the exact flow field. We measure sampling error by the squared Wasserstein distance between the target distribution and the final distribution produced by the midpoint sampler. We show that the standard conditional optimal transport (CondOT) schedule cancels the leading midpoint error and improves the general convergence bound, even when the sampling steps are unequally spaced. On a uniform grid of SS sampling steps, we fix the signal schedule at αt=tα_t=t and prove the existence of scalar noise schedules βtβ_t that approach the CondOT noise schedule 1−t1-t at rate 1/S1/S and yield exact Gaussian sampling for every sufficiently large SS. Controlled Gaussian experiments illustrate the convergence rates and exact calibration.
Mar 31, 2026

Total Variation Guarantees for Sampling with Stochastic Localization

Motivated by the success of score-based generative models, a number of diffusion-based algorithms have recently been proposed for the problem of sampling from a probability measure whose unnormalized density can be accessed. Among them, Grenioux et al. introduced SLIPS, a sampling algorithm based on Stochastic Localization. While SLIPS exhibits strong empirical performance, no rigorous convergence analysis has previously been provided. In this work, we close this gap by establishing the first guarantee for SLIPS in total variation distance. Under minimal assumptions on the target, our bound implies that the number of steps required to achieve an ε\varepsilon-guarantee scales linearly with the dimension, up to logarithmic factors. The analysis leverages techniques from the theory of score-based generative models and further provides theoretical insights into the empirically observed optimal choice of discretization points.