OpenAlex ·
Randomization Beyond Deterministic Adaptivity in Parallel Sampling
- Published
- Source
- OpenAlex
- Published in
- arXiv (Cornell University)
- DOI
- 10.48550/arxiv.2610.03335
- Original
- Read it at the publisher
- Topics
Abstract
Parallel samplers, including masked diffusion models, generate several coordinates per round from conditional marginals, and their accuracy depends on which coordinates are revealed together. A schedule can be improved in two natural ways: adaptively, by choosing later batches from the values already generated, or by randomization, by drawing the schedule at random. We show that randomization is strictly more powerful. For every $r \geq 1$ we construct a full-support distribution on $9r$ binary coordinates such that every deterministic three-round sampler, even with value-dependent batches and arbitrary product kernels, has forward Kullback-Leibler divergence at least $γr - \log 4$ with $γ\approx 0.0966$, whereas drawing one of four fixed schedules with two fair bits drives the divergence below $18 r β^r$ with $β\approx 0.966$. Both samplers query conditionals of the same target. The separation holds for every fixed number of rounds $T \geq 2$, a strict advantage survives perturbations of the target and errors in the conditional predictor, and exact rational arithmetic certifies the gap at nine coordinates, where trained neural predictors preserve it. The mechanism is a hidden mixture: each schedule preserves the dependence pattern of one component, while no deterministic first batch can serve them all.
The authors’ abstract, as arXiv lists it. arXiv’s listings, abstracts included, are free for anyone to reuse.
Read it on ReadSearch
Each opens after you create an account, and brings you back to this paper.
More in Artificial Intelligence
Shapley-based Structural Analysis of Neural Calibration for Stochastic Volatility Models
The Right Wing of the SABR Smile with an Absorbing Boundary: Resolution of Conjectures of Henry-Labordère
Probability flow ODEs in score-based and reflected diffusion models
Efficient Mass Matrix Estimation with Gaussian Cooling
Local Asymptotics for Entrance Laws of Reflected Lévy Excursions
Get the few papers worth your time in Artificial Intelligence every morning.
ReadSearch reads the new papers in your field each day and brings you the few worth reading, each with its key finding in a sentence.