A policy network learns to choose unmasking order in masked diffusion by reweighting the loss, outperforming random and heuristic baselines on ordering-sensitive tasks.
Nearly d-linear convergence bounds for diffu- sion models via stochastic localization.arXiv preprint arXiv:2308.03686
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
Polynomial-time algorithm samples the Sherrington-Kirkpatrick Gibbs measure at beta < 1/2 with o(1) TVD error by combining potential Hessian ascent, stochastic localization, covariance estimates, and Jarzynski equality with rejection sampling.
Discrete Stochastic Localization lets a single trained network support an entire family of per-token SNR paths for discrete sequence generation, with masked diffusion as a special case, and improves MAUVE scores when fine-tuning pretrained checkpoints.
SCSI iteratively refines a self-consistent transport map to invert black-box corruptions and enable generative modeling of clean data.
FM4PDE applies flow matching to learn joint PDE coefficient-solution distributions, using guided sampling with composite losses for forward and inverse problems and providing error guarantees under stated assumptions.
SiLD is a score-matching framework that learns both manifold projection and intrinsic density from a single objective, with proven sample complexity depending only on intrinsic dimension.
Training and sampling in static scalar energy generative models are two instances of the same Lyapunov-driven density transport dynamics on Wasserstein space, differing only by initial condition, which yields a finite stopping criterion for Langevin sampling and additive composition rules that keep
A plug-in estimator for tilted distributions is minimax-optimal, with Wasserstein closeness bounds to the true tilted distribution and TV-accuracy guarantees when running diffusion on the estimated samples.
Diffusion models on manifold-supported data admit score decompositions whose statistical rates are controlled by intrinsic dimension and curvature.
HYVINT introduces an intensity-driven incidence mechanism and tractable variational estimator for hypergraph generation, with error bounds and empirical gains in fidelity, novelty, and diversity.
citing papers explorer
-
Generating DDPM-based Samples from Tilted Distributions
A plug-in estimator for tilted distributions is minimax-optimal, with Wasserstein closeness bounds to the true tilted distribution and TV-accuracy guarantees when running diffusion on the estimated samples.
- Proximal-Based Generative Modeling for Bayesian Inverse Problems