Efficient Perplexity Bound and Ratio Matching in Discrete Diffusion Language Models

• URL: http://arxiv.org/abs/2507.04341v1
• Date: Sun, 06 Jul 2025 10:54:37 GMT
• Title: Efficient Perplexity Bound and Ratio Matching in Discrete Diffusion Language Models
• Authors: Etrit Haxholli, Yeti Z. Gürbüz, Oğul Can, Eli Waxman,
• Abstract summary: We introduce three new theorems concerning the KL divergence between the data and learned distribution.<n>We empirically show that ratio-matching performed by minimizing the denoising cross-entropy between the clean and corrupted data enables models to outperform those utilizing score-entropy.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While continuous diffusion models excel in modeling continuous distributions, their application to categorical data has been less effective. Recent work has shown that ratio-matching through score-entropy within a continuous-time discrete Markov chain (CTMC) framework serves as a competitive alternative to autoregressive models in language modeling. To enhance this framework, we first introduce three new theorems concerning the KL divergence between the data and learned distribution. Our results serve as the discrete counterpart to those established for continuous diffusion models and allow us to derive an improved upper bound of the perplexity. Second, we empirically show that ratio-matching performed by minimizing the denoising cross-entropy between the clean and corrupted data enables models to outperform those utilizing score-entropy with up to 10% lower perplexity/generative-perplexity, and 15% faster training steps. To further support our findings, we introduce and evaluate a novel CTMC transition-rate matrix that allows prediction refinement, and derive the analytic expression for its matrix exponential which facilitates the computation of conditional ratios thus enabling efficient training and generation.

Related papers

• T3: Test-Time Model Merging in VLMs for Zero-Shot Medical Imaging Analysis [15.624549727053475]
  Existing model-merging techniques fail to deliver consistent gains across diverse medical modalities.<n>We introduce Test-Time Task adaptive merging (T3), a backpropagation-free framework that computes per-sample coefficients.<n>We present a rigorous cross-evaluation protocol spanning in-domain, base-to-novel, and corruptions across four modalities.
  arXiv  Detail & Related papers  (2025-10-31T08:05:40Z)
• Operator-Informed Score Matching for Markov Diffusion Models [9.680266522150495]
  Diffusion models are typically trained using score matching, a learning objective to the underlying noising process that guides the model.<n>This paper argues that Markov noising processes enjoy an advantage over alternatives, as the Markov operators that govern the noising process are well-understood.
  arXiv  Detail & Related papers  (2024-06-13T13:07:52Z)
• Convergence Analysis of Discrete Diffusion Model: Exact Implementation through Uniformization [17.535229185525353]
  We introduce an algorithm leveraging the uniformization of continuous Markov chains, implementing transitions on random time points. Our results align with state-of-the-art achievements for diffusion models in $mathbbRd$ and further underscore the advantages of discrete diffusion models in comparison to the $mathbbRd$ setting.
  arXiv  Detail & Related papers  (2024-02-12T22:26:52Z)
• Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution [67.9215891673174]
  We propose score entropy as a novel loss that naturally extends score matching to discrete spaces. We test our Score Entropy Discrete Diffusion models on standard language modeling tasks.
  arXiv  Detail & Related papers  (2023-10-25T17:59:12Z)
• Information-Theoretic Diffusion [18.356162596599436]
  Denoising diffusion models have spurred significant gains in density modeling and image generation. We introduce a new mathematical foundation for diffusion models inspired by classic results in information theory.
  arXiv  Detail & Related papers  (2023-02-07T23:03:07Z)
• Score-based Continuous-time Discrete Diffusion Models [102.65769839899315]
  We extend diffusion models to discrete variables by introducing a Markov jump process where the reverse process denoises via a continuous-time Markov chain. We show that an unbiased estimator can be obtained via simple matching the conditional marginal distributions. We demonstrate the effectiveness of the proposed method on a set of synthetic and real-world music and image benchmarks.
  arXiv  Detail & Related papers  (2022-11-30T05:33:29Z)
• How Much is Enough? A Study on Diffusion Times in Score-based Generative Models [76.76860707897413]
  Current best practice advocates for a large T to ensure that the forward dynamics brings the diffusion sufficiently close to a known and simple noise distribution. We show how an auxiliary model can be used to bridge the gap between the ideal and the simulated forward dynamics, followed by a standard reverse diffusion process.
  arXiv  Detail & Related papers  (2022-06-10T15:09:46Z)
• Comparing Probability Distributions with Conditional Transport [63.11403041984197]
  We propose conditional transport (CT) as a new divergence and approximate it with the amortized CT (ACT) cost. ACT amortizes the computation of its conditional transport plans and comes with unbiased sample gradients that are straightforward to compute. On a wide variety of benchmark datasets generative modeling, substituting the default statistical distance of an existing generative adversarial network with ACT is shown to consistently improve the performance.
  arXiv  Detail & Related papers  (2020-12-28T05:14:22Z)
• Improving the Reconstruction of Disentangled Representation Learners via Multi-Stage Modeling [54.94763543386523]
  Current autoencoder-based disentangled representation learning methods achieve disentanglement by penalizing the ( aggregate) posterior to encourage statistical independence of the latent factors. We present a novel multi-stage modeling approach where the disentangled factors are first learned using a penalty-based disentangled representation learning method. Then, the low-quality reconstruction is improved with another deep generative model that is trained to model the missing correlated latent variables.
  arXiv  Detail & Related papers  (2020-10-25T18:51:15Z)
• Autoregressive Score Matching [113.4502004812927]
  We propose autoregressive conditional score models (AR-CSM) where we parameterize the joint distribution in terms of the derivatives of univariable log-conditionals (scores) For AR-CSM models, this divergence between data and model distributions can be computed and optimized efficiently, requiring no expensive sampling or adversarial training. We show with extensive experimental results that it can be applied to density estimation on synthetic data, image generation, image denoising, and training latent variable models with implicit encoders.
  arXiv  Detail & Related papers  (2020-10-24T07:01:24Z)
• Modeling Score Distributions and Continuous Covariates: A Bayesian Approach [8.772459063453285]
  We develop a generative model of the match and non-match score distributions over continuous covariates. We use mixture models to capture arbitrary distributions and local basis functions. Three experiments demonstrate the accuracy and effectiveness of our approach.
  arXiv  Detail & Related papers  (2020-09-21T02:41:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.