paper-with-me

Papers

Tail Annealing for Heavy-Tailed Flow Matching

2026-05-19 · Jean Pachebat arxiv

Standard generative models struggle with heavy-tailed data: Lipschitz architectures cannot produce power-law tails from Gaussian noise, and interpolating between heavy-tailed data and Gaussians is ill-posed. We propose a simple fix: apply the soft-log transform $φ(x) = \mathrm{sign}(x) \cdot \log(1 + |x|)$ coordinate-wise to data before training, then exponentiate samples after generation. A Hill diagnostic decides per-coordinate whether to transform, leaving light-tailed margins untouched at no added complexity. This compresses heavy tails into a range where standard flow matching succeeds, without heavy-tailed base distributions or architectural modifications. We provide theoretical intuition for why this works: the log-transform maps Pareto tails to exponentials, and the induced dynamics implement a form of tail annealing via power transformations. On a 144-configuration multivariate benchmark (3 copulas, $d$ up to 100, 4 tail indices), Log-FM dominates specialized baselines on $W_1$, CVaR$_{99}$, and extreme-quantile metrics, and is the only method with zero severe divergences across 2{,}880 runs.

📄 PDF Abstract BibTeX arXiv:2605.20068

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Mirror Flow Matching with Heavy-Tailed Priors for Generative Modeling on Convex Domains

2025-10-10 · Yunrui Guan, Krishnakumar Balasubramanian, Shiqian Ma arxiv

We study generative modeling on convex domains using flow matching and mirror maps, and identify two fundamental challenges. First, standard log-barrier mirror maps induce heavy-tailed dual distributions, leading to ill-…

Self-Regulating Annealing in Heavy-Tailed Diffusion Models

2026-06-01 · Keito Wakatsuki, Hideaki Shimazaki arxiv

Diffusion models have emerged as a leading framework for deep generative modeling. While the standard Gaussian formulation is theoretically convenient, its suitability for heavy-tailed datasets remains unclear. To addres…

Heavy-Tailed Diffusion Models

2024-10-18 · Kushagra Pandey, Jaideep Pathak, Yilun Xu, Stephan Mandt 외

Diffusion models achieve state-of-the-art generation quality across many applications, but their ability to capture rare or extreme events in heavy-tailed distributions remains unclear. In this work, we show that traditi…

Denoising

Correcting Source Mismatch in Flow Matching with Radial-Angular Transport

2026-04-05 · Fouad Oubari, Mathilde Mougeot arxiv

Flow Matching is typically built from Gaussian sources and Euclidean probability paths. For heavy-tailed or anisotropic data, however, a Gaussian source induces a structural mismatch already at the level of the radial di…

Heavy-tailed Linear Bandits: Adversarial Robustness, Best-of-both-worlds, and Beyond

2025-08-19 · Canzhe Zhao, Shinji Ito, Shuai Li arxiv

Heavy-tailed bandits have been extensively studied since the seminal work of \citet{Bubeck2012BanditsWH}. In particular, heavy-tailed linear bandits, enabling efficient learning with both a large number of arms and heavy…

Adversarial RobustnessMulti-Armed Bandits