English
Related papers

Related papers: Analytic Bijections for Smooth and Interpretable N…

200 papers

Normalizing flows are constructed from a base distribution with a known density and a diffeomorphism with a tractable Jacobian. The base density of a normalizing flow can be parameterised by a different normalizing flow, thus allowing maps…

Machine Learning · Computer Science 2022-11-07 Samuel Klein , John Andrew Raine , Tobias Golling

The distinctive architectural features of normalizing flows (NFs), notably bijectivity and tractable Jacobians, make them well-suited for generative modeling. Invertible neural networks (INNs) build on these principles to address supervised…

Machine Learning · Computer Science 2026-02-25 Shubhanshu Shekhar , Mohammad Javad Khojasteh , Ananya Acharya , Tony Tohme , Kamal Youcef-Toumi

Normalizing flows are a powerful technique for obtaining reparameterizable samples from complex multimodal distributions. Unfortunately, current approaches are only available for the most basic geometries and fall short when the underlying…

Machine Learning · Statistics 2021-05-03 Luca Falorsi

This paper shows that the Ablowitz-Ladik hierarchy of equations (a well-known integrable discretization of the Non-linear Schrodinger system) can be explicitly viewed as a hierarchy of commuting flows which: (a) are Hamiltonian with respect…

Symplectic Geometry · Mathematics 2009-11-11 Nicholas M. Ercolani , Guadalupe I. Lozano

Incompressible stationary flows of ideal plasma are observed. By introduction of curvilinear system of coordinates in which streamlines and magnetic force lines form a family of coordinate surfaces, MHD equations are partially integrated…

Mathematical Physics · Physics 2010-08-05 Sergey V. Golovin

Conditional normalizing flows can generate diverse image samples for solving inverse problems. Most normalizing flows for inverse problems in imaging employ the conditional affine coupling layer that can generate diverse images quickly.…

Computer Vision and Pattern Recognition · Computer Science 2023-03-17 Seongmin Hong , Inbum Park , Se Young Chun

This article provides a computational evaluation of the popular high resolution upwind WACEB, CUBISTA and ADBQUICKEST schemes for solving non-linear fluid dynamics problems. By using the finite difference methodology, the schemes are…

Normalizing flows (NFs) provide exact likelihoods and deterministic invertible sampling, but have historically lagged behind diffusion models for large-scale image generation. We identify a key obstacle: NFs are required to learn a single…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Longtao Jiang , Jianmin Bao , Zhendong Wang , Xin Tao , Pengfei Wan , Zhihui Li , Xiaojun Chang

The rational quantum algebraically integrable systems are non-trivial generalizations of Laplacian operators to the case of elliptic operators with variable coefficients. We study corresponding extensions of Laplacian growth connected with…

Exactly Solvable and Integrable Systems · Physics 2019-02-26 Anne Boutet de Monvel , Igor Loutsenko , Oksana Yermolayeva

We present a surprisingly new connection between two well-studied combinatorial classes: rooted connected chord diagrams on one hand, and rooted bridgeless combinatorial maps on the other hand. We describe a bijection between these two…

Combinatorics · Mathematics 2017-10-18 Julien Courtiel , Karen Yeats , Noam Zeilberger

Normalizing flows are an essential alternative to GANs for generative modelling, which can be optimized directly on the maximum likelihood of the dataset. They also allow computation of the exact latent vector corresponding to an image…

Machine Learning · Computer Science 2021-08-10 Sandeep Nagar , Marius Dufraisse , Girish Varma

We aim to completely formalize the rough topological analysis of integrable Hamiltonian systems admitting analytical solutions such that the initial phase variables along with the time derivatives of the auxiliary variables are expressed as…

Exactly Solvable and Integrable Systems · Physics 2013-09-30 Mikhail P. Kharlamov

We develop interconnections between the complex normalizing flow for data drawn from Borel probability measures on the twofold realification of the complex manifold and a nonlinear flow nearly K\"ahler-Ricci. The complex normalizing flow…

Differential Geometry · Mathematics 2026-05-15 Andrew Gracyk

Numerous applications of machine learning involve representing probability distributions over high-dimensional data. We propose autoregressive quantile flows, a flexible class of normalizing flow models trained using a novel objective based…

Machine Learning · Computer Science 2023-02-17 Phillip Si , Allan Bishop , Volodymyr Kuleshov

We propose an expert-elicitation method for learning non-parametric joint prior distributions using normalizing flows. Normalizing flows are a class of generative models that enable exact, single-step density evaluation and can capture…

Methodology · Statistics 2025-04-22 Florence Bockting , Stefan T. Radev , Paul-Christian Bürkner

The aim of this paper is to build a theory of commutative and noncommutative {\it injective} valuations of various algebras (including algebras with zero divisors). The targets of our valuations are (well-)ordered commutative and…

Rings and Algebras · Mathematics 2025-08-20 Arkady Berenstein , Dima Grigoriev

In this paper, we consider incompressible Euler flows in $ \mathbb{R}^{4} $ under bi-rotational symmetry, namely solutions that are invariant under rotations in $\mathbb{R}^{4}$ fixing either the first two or last two axes. With the…

Analysis of PDEs · Mathematics 2024-02-29 Kyudong Choi , In-Jee Jeong , Deokwoo Lim

We construct a bijection between admissible representations for an affine Lie algebra $\mathfrak{g}$ at boundary admissible levels and $\mathbb{C}^\times$ fixed points in homogeneous elliptic affine Springer fibres for the Langlands dual…

Representation Theory · Mathematics 2024-04-03 Peng Shan , Dan Xie , Wenbin Yan

We solve the problem of topological classification for smooth structurally stable flows on closed four-dimensional manifolds, the non-wandering set of which contains exactly two saddle equilibria, and the wandering set contains isolated…

Dynamical Systems · Mathematics 2026-03-10 Elena Gurevich

We focus on a branch of region-based spatial logics dealing with affine geometry. The research on this topic is scarce: only a handful of papers investigate such systems, mostly in the case of the real plane. Our long-term goal is to…

Logic in Computer Science · Computer Science 2026-03-18 Adam Trybus