Metraipolis › archive › dc_69dccc015d16
On the Generation Order in GFlowNets — arXiv:2610.41648
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.41648
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-02T07:50:53.977Z
- SHA-256 of the archived text
1f31177a183736a7c864f39b68ab59b09ac8280da04aea194895ffd4b54545d3- Stable URL of this page
https://metraipolis.com/documento/dc_69dccc015d16
How to cite
On the Generation Order in GFlowNets — arXiv:2610.41648 — arXiv (en), https://arxiv.org/abs/2610.41648 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_69dccc015d16 (Metraipolis archive dc_69dccc015d16, sha256 1f31177a183736a7c864f39b68ab59b09ac8280da04aea194895ffd4b54545d3)
BibTeX
@misc{dc69dccc015d16,
title = {On the Generation Order in GFlowNets — arXiv:2610.41648},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.41648},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_69dccc015d16; sha256 1f31177a183736a7c864f39b68ab59b09ac8280da04aea194895ffd4b54545d3},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41648. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Sampling from discrete distributions specified by unnormalised probability functions is a classical statistical problem. GFlowNets address this problem by constructing objects sequentially, adding one discrete component at a time in either a predefined or a learned order. The choice of order determines which conditional distributions the neural network must learn, some of which may be easier to learn than others. Yet whether existing GFlowNet algorithms discover interpretable generation orders and make use of them during training remains unexplored. We introduce controlled problems where generation order is experimentally shown to affect convergence and standard GFlowNet training struggles to discover useful orders. To address this difficulty, we develop Learning-Order GFlowNet, a training recipe that learns interpretable generation orders without order annotations and improves convergence on these problems. Finally, we investigate gradient signal-to-noise ratio (SNR) as a possible explanation for order emergence: orders associated with faster convergence exhibit higher SNR at comparable validation loss, suggesting both a mechanism favouring their emergence and an SNR-based characterisation of a good generation order. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.41648 — 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 2026-11-02T07:40:00.199Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).