Metraipolis › archive › dc_db2fb50ca3cd

Evolutionary One-Step Generators: Fast and Diverse Sampling for Discrete Design — arXiv:2610.08367

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.08367
License (as archived): CC0-1.0
Archived: 2026-10-07T11:41:45.214Z
SHA-256 of the archived text: 1a6bf521bd8fe4c67f545f9a07bfabd6b5d709d38636349a192dd03b938d2a3a
Stable URL of this page: https://metraipolis.com/documento/dc_db2fb50ca3cd

How to cite

Evolutionary One-Step Generators: Fast and Diverse Sampling for Discrete Design — arXiv:2610.08367 — arXiv (en), https://arxiv.org/abs/2610.08367 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_db2fb50ca3cd (Metraipolis archive dc_db2fb50ca3cd, sha256 1a6bf521bd8fe4c67f545f9a07bfabd6b5d709d38636349a192dd03b938d2a3a)

BibTeX

@misc{dcdb2fb50ca3cd,
  title = {Evolutionary One-Step Generators: Fast and Diverse Sampling for Discrete Design — arXiv:2610.08367},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.08367},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_db2fb50ca3cd; sha256 1a6bf521bd8fe4c67f545f9a07bfabd6b5d709d38636349a192dd03b938d2a3a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.08367. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Several discrete design tasks, such as molecular discovery, require diverse collections of useful candidates at low computational cost. High validity alone does not guarantee a useful candidate library: repeatedly generating the same valid structures leaves few distinct alternatives. Training for both feasibility and diversity is challenging because many relevant criteria can only be evaluated after hard decoding. To address this challenge, we propose EGO (Evolutionary Generators with One-step inference), a framework for training compact generators directly on discrete outputs. The method combines distribution matching with structural constraints and optional diversity or history-dependent rewards, using antithetic low-rank evolution strategies without requiring criterion-specific differentiable surrogates. Once trained, the generator produces the entire graph in a single neural-network evaluation. On molecular generation benchmarks, our compact generator achieves over $50\times$ the valid-and-unique yield per estimated dense operation compared to recent one-step flow-map baselines while retaining high chemical validity. In scaffold completion, EGO achieves an observed $44.3\times$ speedup over MoLeR in generation to SMILES and produces approximately $10\times$ as many filter-passing proposals within matched time budgets for generation and screening. Beyond chemistry, EGO produces $1.54\times$ as many distinct held-out elite architectures as relaxed gradient training on NAS-Bench-101. The low generation cost may enable real-time candidate generation across discrete design tasks, supporting interactive exploration of constrained design spaces and rapid construction of candidate sets for downstream evaluation.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Neural and Evolutionary Computing (cs.NE).
Pagina del lavoro: https://arxiv.org/abs/2610.08367 — 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 2026-10-07T11:19:24.826Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).