REVIEW 7 cited by
Score-based Continuous-time Discrete Diffusion Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Score-based modeling through stochastic differential equations (SDEs) has provided a new perspective on diffusion models, and demonstrated superior performance on continuous data. However, the gradient of the log-likelihood function, i.e., the score function, is not properly defined for discrete spaces. This makes it non-trivial to adapt \textcolor{\cdiff}{the score-based modeling} to categorical data. In this paper, we extend diffusion models to discrete variables by introducing a stochastic jump process where the reverse process denoises via a continuous-time Markov chain. This formulation admits an analytical simulation during backward sampling. To learn the reverse process, we extend score matching to general categorical data and show that an unbiased estimator can be obtained via simple matching of the conditional marginal distributions. We demonstrate the effectiveness of the proposed method on a set of synthetic and real-world music and image benchmarks.
Forward citations
Cited by 7 Pith papers
-
Gumbel Distillation for Parallel Text Generation
Conditioning parallel decoders on Gumbel noise sampled from an autoregressive teacher's Gumbel-Max process improves generation quality on LM1B and OpenWebText.
-
Ordering-based Causal Discovery via Generalized Score Matching
Discrete scores—reciprocal singleton conditionals—can identify leaf nodes and recover causal orders when child local distributions are no less random than parent ones.
-
CANDI: Hybrid Discrete-Continuous Diffusion Models
CANDI combines masked and Gaussian corruption in one noising process, letting discrete diffusion models use continuous gradients for joint updates and guidance.
-
Guided Unconditional and Conditional Generative Models for Super-Resolution and Inference of Quasi-Geostrophic Turbulence
Conditional diffusion models outperform guided unconditional models for super-resolving quasi-geostrophic turbulence, especially from sparse and gappy observations.
-
UniCMs: A Unified Consistency Model For Efficient Multimodal Generation and Understanding
UniCMs applies consistency distillation to a unified multimodal transformer, treating image mask-diffusion steps and text parallel-decoding steps as one shared denoising trajectory, enabling 2 to 8 step generation and...
-
Solving Inverse Problems via Diffusion-Based Priors: An Approximation-Free Ensemble Sampling Approach
A weighted-particle sampler evolves the posterior through the diffusion model's reverse dynamics, with theoretical error bounds and improved image reconstructions.
-
Tabular Diffusion Counterfactual Explanations
TDCE guides a tabular diffusion reverse process with Gumbel-softmax classifier gradients to produce counterfactual explanations, achieving high validity on four benchmarks.
Discussion (0). Continue with ORCID to comment.