Metraipolis › archive › dc_49efeae10cd5

Multi-Objective Generative Optimization via Expected Hypervolume Fine-Tuning — arXiv:2611.05207

Source

arXiv (en)

Original

https://arxiv.org/abs/2611.05207

License (as archived)

CC0-1.0

Archived

2026-11-04T21:52:28.100Z

SHA-256 of the archived text

9a0367a587784dc3a9812a29e085937f269a00c29a2b4927a2e54c9f73939c96

Stable URL of this page

https://metraipolis.com/documento/dc_49efeae10cd5

How to cite

Multi-Objective Generative Optimization via Expected Hypervolume Fine-Tuning — arXiv:2611.05207 — arXiv (en), https://arxiv.org/abs/2611.05207 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_49efeae10cd5 (Metraipolis archive dc_49efeae10cd5, sha256 9a0367a587784dc3a9812a29e085937f269a00c29a2b4927a2e54c9f73939c96)

@misc{dc49efeae10cd5,
  title = {Multi-Objective Generative Optimization via Expected Hypervolume Fine-Tuning — arXiv:2611.05207},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.05207},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_49efeae10cd5; sha256 9a0367a587784dc3a9812a29e085937f269a00c29a2b4927a2e54c9f73939c96},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.05207. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Scientific discovery requires plausible designs spanning useful trade-offs among competing properties: a molecule with strong binding affinity, for example, may be difficult to synthesize. Pretrained generative models, e.g., flow and diffusion generators, provide a foundation for proposing such designs, but steering them toward high-quality, complementary trade-offs remains challenging. Inference-time search incurs high per-sample costs, while fine-tuning typically relies on fixed per-candidate rewards that do not capture how designs complement one another. We introduce Hypervolume Fine-Tuning (HVFT), which adapts a single pretrained generator to maximize the expected hypervolume of its samples while controlling departure from the pretrained distribution. Expected hypervolume jointly rewards candidate quality and collective trade-off coverage. Nonetheless, we show that it cannot be expressed as the expectation of a fixed per-candidate reward and therefore cannot be optimized directly with standard techniques. A key observation of this work is that its first variation corresponds to the expected marginal hypervolume contribution of a candidate, which yields a tractable adaptive reward via an unbiased estimator based on model samples. HVFT uses this reward to decompose the objective into a sequence of KL-proximal scalar-reward subproblems. We establish concavity, relative smoothness, and convergence guarantees for the resulting distributional procedure. Across therapeutic-peptide and molecular design tasks spanning discrete diffusion and continuous flow-matching models, HVFT achieves state-of-the-art expected hypervolume and trade-off coverage.

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/2611.05207 — 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 2026-11-04T21:38:49.760Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).