Metraipolis › archive › dc_08997c7e00a7

Fine-Tuning Generative Models for Extreme Events via CVaR-Penalized Wasserstein Gradient Flows — arXiv:2608.11544

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.11544
License (as archived): CC0-1.0
Archived: 2026-10-19T05:40:15.523Z
SHA-256 of the archived text: 7d82af58d674d70a3b5b7a39458d59fd8d5ced157f0787f447e02f0bc5d6fd82
Stable URL of this page: https://metraipolis.com/documento/dc_08997c7e00a7

How to cite

Fine-Tuning Generative Models for Extreme Events via CVaR-Penalized Wasserstein Gradient Flows — arXiv:2608.11544 — arXiv (en), https://arxiv.org/abs/2608.11544 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_08997c7e00a7 (Metraipolis archive dc_08997c7e00a7, sha256 7d82af58d674d70a3b5b7a39458d59fd8d5ced157f0787f447e02f0bc5d6fd82)

BibTeX

@misc{dc08997c7e00a7,
  title = {Fine-Tuning Generative Models for Extreme Events via CVaR-Penalized Wasserstein Gradient Flows — arXiv:2608.11544},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.11544},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_08997c7e00a7; sha256 7d82af58d674d70a3b5b7a39458d59fd8d5ced157f0787f447e02f0bc5d6fd82},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.11544. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In many high-stakes domains, extreme events carry substantial consequences, yet learning the heavy-tailed distributions that govern them from finite samples remains challenging: the quantities of interest are driven by a few extreme observations, so the tail is under-sampled relative to its importance. Even generative models tailored for heavy tails capture the tail region inadequately in practice. We propose the Conditional Value-at-Risk (CVaR)-penalized Generative Particle Algorithm (CVaR-GPA), a tail-agnostic algorithm for fine-tuning generative models toward heavy-tailed targets, built as a time discretization of the Wasserstein gradient flow of the Lipschitz-regularized KL divergence penalized by a CVaR discrepancy term. Such a flow can be initialized from the output samples of the pre-trained model, which are then transported along the gradient descent of the loss functional, without requiring access to the pre-trained model's internal architecture. The Lipschitz-regularized KL divergence requires minimal assumptions on the target, while the CVaR penalty focuses the flow on the tail. The CVaR penalty depends on the target only through a scalar tail statistic, inducing a velocity field that remains active in the under-sampled tail region at a dimension-free estimation cost. The resulting velocity field, and hence the depth of the transport map, implicitly adapts to the target, without target-specific modifications. Across four targets, including two real-world, high-dimensional datasets (daily streamflow in the Ohio River basin ($d=64$) and the Fama-French portfolios ($d=25$) with tail indices ranging from $1.05$ to $3.34$), fine-tuning with CVaR-GPA reduces global and tail errors by geometric-mean factors of $14.0 \times$ and $9.8 \times$, respectively, across seven pre-trained models spanning GANs, diffusion models, and other generative flows, with a single set of hyperparameters.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-13 in cs.LG).
Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.11544 — 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 2026-10-19T05:18:32.536Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-13?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).