English
Related papers

Related papers: Tails of Lipschitz Triangular Flows

200 papers

This paper regroups some of the basic properties of Lipschitz maps and their flows. Many of the results presented here are classical in the case of smooth maps. We prove them here in the Lipschitz case for a better understanding of the…

Classical Analysis and ODEs · Mathematics 2019-01-23 Youness Boutaib

This paper investigates the connections between rectified flows, flow matching, and optimal transport. Flow matching is a recent approach to learning generative models by estimating velocity fields that guide transformations from a source…

Machine Learning · Computer Science 2026-02-17 Johannes Hertrich , Antonin Chambolle , Julie Delon

Normalizing flows are an established approach for modelling complex probability densities through invertible transformations from a base distribution. However, the accuracy with which the target distribution can be captured by the…

Machine Learning · Statistics 2024-02-02 Harry Bevins , Will Handley , Thomas Gessey-Jones

Under general assumptions on the target distribution $p^\star$, we establish a sharp Lipschitz regularity theory for flow-matching vector fields and diffusion-model scores, with optimal dependence on time and dimension. As applications, we…

Statistics Theory · Mathematics 2026-04-08 Arthur Stéphanovitch

We investigate stochastic interpolation, a recently introduced framework for high dimensional sampling which bears many similarities to diffusion modeling. Stochastic interpolation generates a data sample by first randomly initializing a…

Statistics Theory · Mathematics 2025-10-28 Mara Daniels

One among several advantages of measure transport methods is that they allow for a unified framework for processing and analysis of data distributed according to a wide class of probability measures. Within this context, we present results…

Quantitative Methods · Quantitative Biology 2024-05-14 Vanessa Lopez-Marrero , Patrick R. Johnstone , Gilchan Park , Xihaier Luo

Local conservation of mass and entropy are becoming increasingly desirable properties for modern numerical weather and climate models. This work presents a Flux-Form Semi-Lagrangian (FFSL) transport scheme, called SWIFT, that facilitates…

Numerical Analysis · Mathematics 2024-10-31 Thomas M. Bendall , James Kent

Nowadays in density estimation, posterior rates of convergence for location and location-scale mixtures of Gaussians are only known under light-tail assumptions; with better rates achieved by location mixtures. It is conjectured, but not…

Statistics Theory · Mathematics 2016-08-24 Zacharie Naulet , Judith Rousseau

Diffusion models have emerged as powerful generative frameworks with widespread applications across machine learning and artificial intelligence systems. While current research has predominantly focused on linear diffusions, these…

Machine Learning · Statistics 2025-10-06 Kulunu Dharmakeerthi , Yousef El-Laham , Henry H. Wong , Vamsi K. Potluru , Changhong He , Taosong He

We investigate front propagation in systems with diffusive and sub-diffusive behavior. The scaling behavior of moments of the diffusive problem, both in the standard and in the anomalous cases, is not enough to determine the features of the…

Statistical Mechanics · Physics 2016-09-06 Maurizio Serva , Davide Vergni , Angelo Vulpiani

Transport maps can ease the sampling of distributions with non-trivial geometries by transforming them into distributions that are easier to handle. The potential of this approach has risen with the development of Normalizing Flows (NF)…

Machine Learning · Statistics 2024-02-20 Louis Grenioux , Alain Durmus , Éric Moulines , Marylou Gabrié

We study scale-invariant systems in the presence of Gaussian quenched electric disorder, focusing on the tails of the energy spectra induced by disorder. For relevant disorder we derive asymptotic expressions for the densities of…

Disordered Systems and Neural Networks · Physics 2012-07-17 Sho Yaida

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 traditional diffusion and…

Machine Learning · Computer Science 2024-10-30 Kushagra Pandey , Jaideep Pathak , Yilun Xu , Stephan Mandt , Michael Pritchard , Arash Vahdat , Morteza Mardani

Normalizing flows, a popular class of deep generative models, often fail to represent extreme phenomena observed in real-world processes. In particular, existing normalizing flow architectures struggle to model multivariate extremes,…

Machine Learning · Computer Science 2022-05-04 Andrew McDonald , Pang-Ning Tan , Lifeng Luo

Triangular map is a recent construct in probability theory that allows one to transform any source probability density function to any target density function. Based on triangular maps, we propose a general framework for high-dimensional…

Machine Learning · Computer Science 2019-06-12 Priyank Jaini , Kira A. Selby , Yaoliang Yu

In this paper we consider the Interband Light Absorption Coefficient for various models. We show that at the lower and upper edges of the spectrum the Lifshitz tails behaviour of the density of states implies similar behaviour for the ILAC…

Mathematical Physics · Physics 2009-04-01 W. Kirsch , M. Krishna

The density of states of disordered hopping models generically exhibits an essential singularity around the edges of its support, known as a Lifshitz tail. We study this phenomenon on the Bethe lattice, i.e. for the large-size limit of…

Disordered Systems and Neural Networks · Physics 2011-09-28 Victor Bapst , Guilhem Semerjian

Identifying the generating mechanism of a network is challenging as, more often than not, only snapshots are available, but not the full evolution. One candidate for the generating mechanism is preferential attachment which, in its simplest…

Methodology · Statistics 2025-10-07 Thomas Boughen , Clement Lee , Vianey Palacios Ramirez

We study Flow Matching in a semi-discrete setting where a Gaussian source is transported toward a discrete target supported on finitely many points. This semi-discrete regime is the theoretical setting behind the use of Flow Matching for…

Machine Learning · Computer Science 2026-05-11 Emile Pierret , Johannes Hertrich , Samuel Hurault , Julie Delon

An invertible function is bi-Lipschitz if both the function and its inverse have bounded Lipschitz constants. Nowadays, most Normalizing Flows are bi-Lipschitz by design or by training to limit numerical errors (among other things). In this…

Machine Learning · Computer Science 2024-03-08 Alexandre Verine , Benjamin Negrevergne , Fabrice Rossi , Yann Chevaleyre