English
Related papers

Related papers: Random Growth via Gradient Flow Aggregation

200 papers

Gradient descent (GD) methods for the training of artificial neural networks (ANNs) belong nowadays to the most heavily employed computational schemes in the digital world. Despite the compelling success of such methods, it remains an open…

Optimization and Control · Mathematics 2025-09-01 Shokhrukh Ibragimov , Arnulf Jentzen , Adrian Riekert

We study aggregation driven by a localized source of monomers. The densities become stationary and have algebraic tails far away from the source. We show that in a model with mass-independent reaction rates and diffusion coefficients, the…

Statistical Mechanics · Physics 2015-06-09 P. L. Krapivsky

Training normalizing flow generative models can be challenging due to the need to calculate computationally expensive determinants of Jacobians. This paper studies the likelihood-free training of flows and proposes the energy objective, an…

Machine Learning · Computer Science 2023-06-26 Phillip Si , Zeyi Chen , Subham Sekhar Sahoo , Yair Schiff , Volodymyr Kuleshov

Flow-based generative models are composed of invertible transformations between two random variables of the same dimension. Therefore, flow-based models cannot be adequately trained if the dimension of the data distribution does not match…

Computer Vision and Pattern Recognition · Computer Science 2020-11-17 Hyeongju Kim , Hyeonseung Lee , Woo Hyun Kang , Joun Yeop Lee , Nam Soo Kim

We develop a general mathematical framework to analyze scaling regimes and derive explicit analytic solutions for gradient flow (GF) in large learning problems. Our key innovation is a formal power series expansion of the loss evolution,…

Machine Learning · Computer Science 2026-02-05 Dmitry Yarotsky , Eugene Golikov , Yaroslav Gusev

We develop a fast and scalable numerical approach to solve Wasserstein gradient flows (WGFs), particularly suitable for high-dimensional cases. Our approach is to use general reduced-order models, like deep neural networks, to parameterize…

Numerical Analysis · Mathematics 2024-05-24 Yijie Jin , Shu Liu , Hao Wu , Xiaojing Ye , Haomin Zhou

Global existence and long-time behavior of solutions to a family of nonlinear fourth order evolution equations on $R^d$ are studied. These equations constitute gradient flows for the perturbed information functionals $F[u] = 1/(2\alpha)…

Analysis of PDEs · Mathematics 2009-01-06 Daniel Matthes , Robert J. McCann , Giuseppe Savar'e

Time-sensitive networks require timely and accurate monitoring of the status of the network. To achieve this, many devices send packets periodically, which are then aggregated and forwarded to the controller. Bounding the aggregate…

Networking and Internet Architecture · Computer Science 2023-07-24 Seyed Mohammadhossein Tabatabaee , Anne Bouillard , Jean-Yves Le Boudec

Consider a stochastic growth model on $\mathbb{Z} ^d$. Start with some active particle at the origin and sleeping particles elsewhere. The initial number of particles at $x \in \mathbb{Z} ^d$ is $\eta(x)$, where $\eta (x)$ are independent…

Probability · Mathematics 2023-05-03 Viktor Bezborodov , Tyll Krueger

We consider the evolution of hypersurfaces in $\mathbb{R}^{n+1}$ with normal velocity given by a positive power of the mean curvature. The hypersurfaces under consideration are assumed to be strictly mean convex (positive mean curvature),…

Differential Geometry · Mathematics 2021-04-02 Wolfgang Maurer

Consider a branching random walk $(G_u)_{u\in \mathbb T}$ on the general linear group $\textrm{GL}(V)$ of a finite dimensional space $V$, where $\mathbb T$ is the associated genealogical tree with nodes $u$. For any starting point $v \in V…

Probability · Mathematics 2024-12-11 Ion Grama , Sebastian Mentemeier , Hui Xiao

We study the problem of estimating a sequence of evolving probability distributions from historical data, where the underlying distribution changes over time in a nonstationary and nonparametric manner. To capture gradual changes, we…

Optimization and Control · Mathematics 2025-12-16 Edward J. Anderson , Dominic S. T. Keehan

Flow-based generative models have recently become one of the most efficient approaches to model data generation. Indeed, they are constructed with a sequence of invertible and tractable transformations. Glow first introduced a simple type…

Computer Vision and Pattern Recognition · Computer Science 2022-08-09 Thanh-Dat Truong , Khoa Luu , Chi Nhan Duong , Ngan Le , Minh-Triet Tran

We study the additive functional $X_n(\alpha)$ on conditioned Galton-Watson trees given, for arbitrary complex $\alpha$, by summing the $\alpha$th power of all subtree sizes. Allowing complex $\alpha$ is advantageous, even for the study of…

Probability · Mathematics 2021-04-08 James Allen Fill , Svante Janson

We consider a model of aggregation, both diffusion-limited and ballistic, based on the Cayley tree. Growth is from the leaves of the tree towards the root, leading to non-trivial screening and branch competition effects. The model exhibits…

Soft Condensed Matter · Physics 2009-10-31 M. B. Hastings , Thomas C. Halsey

Generative models have emerged as a powerful paradigm for solving physics systems and modeling complex spatiotemporal dynamics. However, achieving high physical accuracy without incurring high computational cost remains a fundamental…

Machine Learning · Computer Science 2026-05-27 Jiahe Huang , Sihan Xu , Sharvaree Vadgama , Rose Yu

We define and study one-dimensional model of irreversible aggregation of particles obeying a discrete-time kinetics which is a special limit of the generalized Totally Asymmetric Simple Exclusion Process (gTASEP) on open chains. The model…

Statistical Mechanics · Physics 2017-05-10 Nadezhda Zh. Bunzarova , Nina Ch. Pesheva

We consider a time-continuous branching random walk on a one-dimensional lattice on which there is one center (lattice point) of particle generation, called branching source. The generation of particles in the branching source is described…

Probability · Mathematics 2023-12-19 E. Filichkina , E. Yarovaya

A diffusion-limited aggregation process, in which clusters coalesce by means of 3-particle reaction, A+A+A->A, is investigated. In one dimension we give a heuristic argument that predicts logarithmic corrections to the mean-field asymptotic…

Condensed Matter · Physics 2009-10-22 P. L. Krapivsky

Flow Matching, a promising approach in generative modeling, has recently gained popularity. Relying on ordinary differential equations, it offers a simple and flexible alternative to diffusion models, which are currently the…

Machine Learning · Statistics 2026-03-13 Lea Kunkel