English
Related papers

Related papers: Complex normalizing flows can almost be informatio…

200 papers

We proved that on every Stiefel manifold $V_2\mathbb{R}^n\cong \operatorname{SO}(n)/\operatorname{SO}(n-2)$ with $n\ge 3$ the normalized Ricci flow preserves the positivity of the Ricci curvature of invariant Riemannian metrics with…

Differential Geometry · Mathematics 2024-12-05 Nurlan Abiev

Normalizing flows provide an elegant approach to generative modeling that allows for efficient sampling and exact density evaluation of unknown data distributions. However, current techniques have significant limitations in their…

Machine Learning · Computer Science 2022-06-22 Sahil Sidheekh , Chris B. Dock , Tushar Jain , Radu Balan , Maneesh K. Singh

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

For a monic polynomial $Q_n$ of degree $n$, let $Q_{n, k}$ be its $k$-th derivative normalized to be monic. Under the only assumption that the sequence $\{Q_n\}$ has a weak* limiting zero distribution (an empirical distribution of zeros)…

Classical Analysis and ODEs · Mathematics 2025-09-23 Andrei Martinez-Finkelshtein , Evgenii A. Rakhmanov

Based on the manifold hypothesis, real-world data often lie on a low-dimensional manifold, while normalizing flows as a likelihood-based generative model are incapable of finding this manifold due to their structural constraints. So, one…

Machine Learning · Computer Science 2022-06-08 Seyedeh Fatemeh Razavi , Mohammad Mahdi Mehmanchi , Reshad Hosseini , Mostafa Tavassolipour

We have found that the relation between the flow through campylotic (generically curved) media, consisting of randomly located curvature perturbations, and the average Ricci scalar of the system exhibits two distinct functional expressions…

Fluid Dynamics · Physics 2015-08-04 M. Mendoza , S. Succi , H. J. Herrmann

We propose a variational scheme for computing Wasserstein gradient flows. The scheme builds upon the Jordan--Kinderlehrer--Otto framework with the Benamou-Brenier's dynamic formulation of the quadratic Wasserstein metric and adds a…

Numerical Analysis · Mathematics 2020-07-15 Wuchen Li , Jianfeng Lu , Li Wang

We show that for any solution to the K\"ahler-Ricci flow with positive bisectional curvature on a compact K\"ahler manifold $M^n$, the bisectional curvature has a uniform positive lower bound. As a consequence, the solution converges…

Differential Geometry · Mathematics 2010-03-29 Huai-Dong Cao , Meng Zhu

We study the asymptotic behavior of the K\"ahler-Ricci flow on K\"ahler manifolds of nonnegative holomorphic bisectional curvature. Using these results we prove that a complete noncompact K\"ahler manifold with nonnegative bounded…

Differential Geometry · Mathematics 2016-09-07 Albert Chau , Luen-Fai Tam

It was proved by H. Chen earlier that the property of the sum of any two eigenvalues of the curvature operator is positive is preserved under the ricci flow in all dimensional. By a recent result of Phong-Sturm, a similar notion of positive…

Differential Geometry · Mathematics 2007-05-23 X. X. Chen , H. Li

We prove uniform diameter estimates, volume non-collapsing estimates and Gromov-Hausdorff convergence for the normalized Chern-Ricci flow on smooth complex minimal surfaces of general type, starting from an arbitrary Hermitian metric. This…

Differential Geometry · Mathematics 2026-05-22 Haoyuan Sun

Quasi-Einstein manifolds are well-studied generalizations of Einstein manifolds. This includes gradient Ricci solitons and has a natural correspondence with the warped product Einstein manifolds. A quasi-Einstein metric is said to be rigid…

Differential Geometry · Mathematics 2026-04-24 Atreyee Bhattacharya , Sayoojya Prakash

On certain del Pezzo surfaces with large automorphism groups, it is shown that the solution to the K\"ahler-Ricci flow with a certain initial value converges in $C^\infty$-norm exponentially fast to a K\"ahler-Einstein metric. The proof is…

Algebraic Geometry · Mathematics 2007-10-31 Gordon Heier

In this note, we provide some general discussion on the Ricci lower bound along K\"ahler-Ricci flow with singularity over closed manifold.

Differential Geometry · Mathematics 2011-10-28 Zhou Zhang

Efficient gradient computation of the Jacobian determinant term is a core problem in many machine learning settings, and especially so in the normalizing flow framework. Most proposed flow models therefore either restrict to a function…

Machine Learning · Computer Science 2021-06-10 T. Anderson Keller , Jorn W. T. Peters , Priyank Jaini , Emiel Hoogeboom , Patrick Forré , Max Welling

Let us consider a projective manifold and $\Omega$ a volume form. We define the gradient flow associated to the problem of $\Omega$-balanced metrics in the quantum formalism, the \Omega$-balacing flow. At the limit of the quantization, we…

Differential Geometry · Mathematics 2015-11-17 H. -D. Cao , Julien Keller

We study the Kahler-Ricci flow on Fano manifolds. We show that if the curvature is bounded along the flow and if the manifold is K-polystable and asymptotically Chow semistable, then the flow converges exponentially fast to a…

Differential Geometry · Mathematics 2010-04-27 Valentino Tosatti

We first prove a uniform integral Laplace comparison result for the K\"ahler Ricci flow on Fano manifolds which depends only on the initial metric. As an application, using Cheeger-Colding theory and previous results by some of the authors,…

Differential Geometry · Mathematics 2025-10-30 Gang Tian , Qi S. Zhang , Zhenlei Zhang , Meng Zhu , Xiaohua Zhu

S. K. Donaldson asked whether the lower bound of the Calabi functional is achieved by a sequence the normalized Donaldson-Futaki invariants. We answer the question for the Ricci curvature formalism, in place of the scalar curvature. The…

Differential Geometry · Mathematics 2020-01-22 Tomoyuki Hisamoto

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