Metraipolis › archive › dc_d0001b4e4fa2

Regularized Wasserstein Distance for Discrete Generative Modeling and Clustering Analysis — arXiv:2611.00653

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.00653
License (as archived): CC0-1.0
Archived: 2026-11-03T11:24:53.566Z
SHA-256 of the archived text: c8da72a1a0eda09e7a51bed98a32e35fa2385f8403a8fc817c9d4110a11e675c
Stable URL of this page: https://metraipolis.com/documento/dc_d0001b4e4fa2

How to cite

Regularized Wasserstein Distance for Discrete Generative Modeling and Clustering Analysis — arXiv:2611.00653 — arXiv (en), https://arxiv.org/abs/2611.00653 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d0001b4e4fa2 (Metraipolis archive dc_d0001b4e4fa2, sha256 c8da72a1a0eda09e7a51bed98a32e35fa2385f8403a8fc817c9d4110a11e675c)

BibTeX

@misc{dcd0001b4e4fa2,
  title = {Regularized Wasserstein Distance for Discrete Generative Modeling and Clustering Analysis — arXiv:2611.00653},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00653},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d0001b4e4fa2; sha256 c8da72a1a0eda09e7a51bed98a32e35fa2385f8403a8fc817c9d4110a11e675c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00653. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In this paper, we formulate clustering analysis as discrete generative modeling. Specifically, when the generator is restricted to a finite candidate space, the generated samples naturally emerge as the most representative prototypes of the underlying data distribution. To model such a discrete candidate space, we employ a Discrete Distribution Network (DDN). However, DDN suffers from unstable training due to its hard nearest-neighbor selection. To stabilize training and encourage geometric consistency, we replace DDN's l2 loss between images with regularized Wasserstein distance between the empirical distributions of real and generated images. The resulting framework, termed Discrete Generative Clustering (DGC), offers four notable advantages: 1) the learned cluster centers are directly interpretable, as they are realistic synthetic samples; 2) the inference cost scales logarithmically with the number of clusters, i.e., O(log K), making the method scalable to extremely large K; 3) the regularized Wasserstein distance provides a smooth and well-behaved optimization objective that facilitates stable convergence, whereas DDN's l2 loss tends to converge to poor local optima; and 4) DGC replaces DDN's nearest-neighbor selection with random-neighbor selection, which avoids the density shift problem during multi-step forward. Extensive experiments on several benchmarks demonstrate the effectiveness and desirable properties of DGC. The code is publicly available at GitHub.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.00653 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T11:02:37.780Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).