English
Related papers

Related papers: Metric Flows with Neural Networks

200 papers

In this note we explain how a flow in the space of Riemmanian metrics (including Ricci's \cite{mt}) induces one in the space of pseudoconnections.

Differential Geometry · Mathematics 2015-09-28 C. A. Morales

In this paper, we study Discretized Neural Networks (DNNs) composed of low-precision weights and activations, which suffer from either infinite or zero gradients due to the non-differentiable discrete function during training. Most…

Machine Learning · Computer Science 2024-12-20 Jun Chen , Hanwen Chen , Mengmeng Wang , Guang Dai , Ivor W. Tsang , Yong Liu

Convergence of deep neural networks as the depth of the networks tends to infinity is fundamental in building the mathematical foundation for deep learning. In a previous study, we investigated this question for deep ReLU networks with a…

Machine Learning · Computer Science 2022-01-25 Yuesheng Xu , Haizhang Zhang

Physics-based optical flow models have been successful in capturing the deformities in fluid motion arising from digital imagery. However, a common theoretical framework analyzing several physics-based models is missing. In this regard, we…

Computer Vision and Pattern Recognition · Computer Science 2024-06-04 Hirak Doshi , N. Uday Kiran

Previous influential work showed that infinite width limits of neural networks in the lazy training regime are described by kernel machines. Here, we show that neural networks trained in the rich, feature learning infinite-width regime in…

Machine Learning · Computer Science 2025-09-12 Clarissa Lauditi , Blake Bordelon , Cengiz Pehlevan

Wasserstein gradient flows of maximum mean discrepancy (MMD) functionals with non-smooth Riesz kernels show a rich structure as singular measures can become absolutely continuous ones and conversely. In this paper we contribute to the…

Machine Learning · Computer Science 2024-03-22 Fabian Altekrüger , Johannes Hertrich , Gabriele Steidl

There is a common description of different intrinsic geometric flows in two dimensions using Toda field equations associated to continual Lie algebras that incorporate the deformation variable t into their system. The Ricci flow admits zero…

High Energy Physics - Theory · Physics 2009-11-11 I. Bakas

Interpretability is crucial for ensuring RL systems align with human values. However, it remains challenging to achieve in complex decision making domains. Existing methods frequently attempt interpretability at the level of fundamental…

Machine Learning · Computer Science 2025-06-03 Anna Soligo , Pietro Ferraro , David Boyle

Let ${\bf M}$ be a compact Riemannian manifold and the metrics $g=g(t)$ evolve by the Ricci flow. We prove the following result. The Sobolev imbedding by Aubin or Hebey, perturbed by a scalar curvature term and modulo sharpness of…

Differential Geometry · Mathematics 2007-08-29 Qi S. Zhang

Diffusion and flow-based generative models have achieved remarkable success in domains such as image synthesis, video generation, and natural language modeling. In this work, we extend these advances to weight space learning by leveraging…

Machine Learning · Computer Science 2025-10-17 Daniel Saragih , Deyu Cao , Tejas Balaji

Normalizing flows have emerged as an important family of deep neural networks for modelling complex probability distributions. In this note, we revisit their coupling and autoregressive transformation layers as probabilistic graphical…

Machine Learning · Computer Science 2020-06-05 Antoine Wehenkel , Gilles Louppe

A novel method to identify salient computational paths within randomly wired neural networks before training is proposed. The computational graph is pruned based on a node mass probability function defined by local graph measures and…

Machine Learning · Computer Science 2020-07-09 Samuel Glass , Simeon Spasov , Pietro Liò

The matrix-based Renyi's \alpha-entropy functional and its multivariate extension were recently developed in terms of the normalized eigenspectrum of a Hermitian matrix of the projected data in a reproducing kernel Hilbert space (RKHS).…

Machine Learning · Computer Science 2020-01-27 Shujian Yu , Kristoffer Wickstrøm , Robert Jenssen , Jose C. Principe

Numerical approximations to Ricci-flat Calabi--Yau metrics make it possible to move beyond the topological and holomorphic data that have traditionally dominated explicit string compactifications. This article explains what new physics and…

High Energy Physics - Theory · Physics 2026-05-25 Per Berglund , Tristan Hübsch , Vishnu Jejjala

Neural networks often operate in the overparameterized regime, in which there are far more parameters than training samples, allowing the training data to be fit perfectly. That is, training the network effectively learns an interpolating…

Machine Learning · Computer Science 2025-03-19 Suzanna Parkinson , Greg Ongie , Rebecca Willett

Metric measure spaces with synthetic Ricci bounds have attracted great interest in recent years, accompanied by spectacular breakthroughs and deep new insights. In this survey, I will provide a brief introduction to the concept of lower…

Metric Geometry · Mathematics 2024-04-25 Karl-Theodor Sturm

In 2004, Manning showed that the topological entropy of the geodesic flow for a surface of negative curvature decreases as the metric evolves under the normalised Ricci flow. It is an interesting open problem, also due to Manning, to…

Dynamical Systems · Mathematics 2009-12-18 Daniel J. Thompson

Deep neural networks' remarkable ability to correctly fit training data when optimized by gradient-based algorithms is yet to be fully understood. Recent theoretical results explain the convergence for ReLU networks that are wider than…

Machine Learning · Computer Science 2021-02-09 Asaf Noy , Yi Xu , Yonathan Aflalo , Lihi Zelnik-Manor , Rong Jin

We survey some recent developments in the study of collapsing Riemannian manifolds with Ricci curvature bounded below, especially the locally bounded Ricci covering geometry and the Ricci flow smoothing techniques. We then prove that if a…

Differential Geometry · Mathematics 2020-12-01 Shaosai Huang , Xiaochun Rong , Bing Wang

We present a framework to define a large class of neural networks for which, by construction, training by gradient flow provably reaches arbitrarily low loss when the number of parameters grows. Distinct from the fixed-space global…

Optimization and Control · Mathematics 2025-01-13 David A. R. Robin , Kevin Scaman , Marc Lelarge