|国家预印本平台
首页|Discrete Markov Bridge

Discrete Markov Bridge

Discrete Markov Bridge

来源:Arxiv_logoArxiv
英文摘要

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.

Hengli Li、Yuxuan Wang、Song-Chun Zhu、Ying Nian Wu、Zilong Zheng

计算技术、计算机技术

Hengli Li,Yuxuan Wang,Song-Chun Zhu,Ying Nian Wu,Zilong Zheng.Discrete Markov Bridge[EB/OL].(2025-05-26)[2025-06-13].https://arxiv.org/abs/2505.19752.点此复制

评论