Abstract
A novel framework, Discrete Markov Bridge, is introduced for discrete data modeling with Matrix Learning and Score Learning components, demonstrating superior performance compared to existing methods on Text8 and CIFAR-10 datasets.
Discrete diffusion has recently emerged as a promising paradigm in discrete data modeling. However, existing methods typically rely on a fixed rate transition matrix during training, which not only limits the expressiveness of latent representations, a fundamental strength of variational methods, but also constrains the overall design space. To address these limitations, we propose Discrete Markov Bridge, a novel framework specifically designed for discrete representation learning. Our approach is built upon two key components: Matrix Learning and Score Learning. We conduct a rigorous theoretical analysis, establishing formal performance guarantees for Matrix Learning and proving the convergence of the overall framework. Furthermore, we analyze the space complexity of our method, addressing practical constraints identified in prior studies. Extensive empirical evaluations validate the effectiveness of the proposed Discrete Markov Bridge, which achieves an Evidence Lower Bound (ELBO) of 1.38 on the Text8 dataset, outperforming established baselines. Moreover, the proposed model demonstrates competitive performance on the CIFAR-10 dataset, achieving results comparable to those obtained by image-specific generation approaches.
Community
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- Target Concrete Score Matching: A Holistic Framework for Discrete Diffusion (2025)
- Efficient Generative Model Training via Embedded Representation Warmup (2025)
- Fast Autoregressive Models for Continuous Latent Generation (2025)
- Discrete Neural Flow Samplers with Locally Equivariant Transformer (2025)
- Learning Energy-Based Generative Models via Potential Flow: A Variational Principle Approach to Probability Density Homotopy Matching (2025)
- Overcoming Dimensional Factorization Limits in Discrete Diffusion Models through Quantum Joint Distribution Learning (2025)
- A Unified Approach to Analysis and Design of Denoising Markov Models (2025)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper