Newest papers

Density-Level Backward Error for Low-NFE Generative Flows

Ewsey R. Obzherin, Valentin Khrulkov · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.29475 · cited by 0 works (OpenAlex) · open-access PDF

French

L'échantillonnage ODE génératif à faible NFE est restreint non seulement par l'ordre du solveur, mais aussi par la façon dont un budget fixe d'évaluations réseau est distribué le long du flux. Nous développons un cadre d'erreur rétroactive au niveau de la densité qui identifie le composant du défaut d'équation modifiée d'un solveur qui change la marge évolutive, tout en excluant la distorsion de trajectoire solénoïde qui est invisible dans la géométrie tangente fixe de Wasserstein. Le résiduel résultant induit une règle d'allocation de calcul consciente de l'ordre du solveur et, par la liberté de mesure, un objectif pour sélectionner des représentants numériquement favorables

Machine translation (Meta M2M100); the English original follows.

Abstract

Low-NFE generative ODE sampling is constrained not only by solver order, but also by how a fixed budget of network evaluations is distributed along the flow. We develop a density-level backward-error framework that identifies the component of a solver's modified-equation defect that changes the evolving marginal, while excluding solenoidal trajectory distortion that is invisible in Wasserstein tangent geometry. The resulting residual induces a solver-order-aware compute-allocation rule and, through gauge freedom, an objective for selecting numerically favorable velocity representatives of the same density path. This separates our approach from schedule search driven by trajectory or endpoint surrogates and from higher-order solver design. Exact Gaussian and mixture models establish the mechanism, including cases where curvature-based allocation fails and continuum-optimal transport is not discretization-optimal. On a pretrained CIFAR-10 EDM probability-flow ODE, density-aware allocation consistently improves fixed-update Euler sampling in the low-NFE regime. Matched-seed convergence to a dense Euler reference confirms that the method accelerates approximation of the same high-NFE flow rather than changing the asymptotic sampler.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Trajectory, Solver, Residual, Mathematics, Convergence (economics), Applied mathematics

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.29475, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange