Related papers: Discrete scalar curvature as a weighted sum of Ollivier-Ricci curvatures

Related papers

Dimension Reduction for Curves: Simplified and Generalized [56.23281156053955]
We revisit random projections for reducing the dimension of high-dimensional polygonal curves.<n>We give a simplified proof of the known $O(varepsilon-2log(nm))$ bound on the target dimension of a random projection.<n>Our proof is based on the concept of sparse oblivious subspace embeddings.
arXiv Detail & Related papers (2026-07-03T08:48:35Z)
Ricci-Filtration: Boosting Retrieval-Augmented Generation Reranker to Query-Answer Tasks by Discrete Ricci Flow [13.55091281996713]
Ricci-Filtration is a geometry-based RAG reranker enhancement procedure.<n>We show that Ricci-Filtration outperforms several baseline reranking methods in accuracy, precision, recall, and F1 scores.
arXiv Detail & Related papers (2026-06-13T21:34:02Z)
Ollivier-Ricci Curvature of Riemannian Manifolds and Directed Graphs with Applications to Graph Neural Networks [0.0]
This thesis is an exposition of Ollivier-Ricci Curvature of metric spaces as introduced by Yann Ollivier.<n>We present some of the major results and proofs that connect Ollivier-Ricci curvature with classical Ricci curvature.<n>We present novel ideas and proofs regarding extensions of these results to directed graphs, and finally applications of graph-based Ollivier-Ricci curvature algorithms in network science and graph machine learning.
arXiv Detail & Related papers (2026-04-06T22:28:17Z)
Sobolev--Ricci Curvature [12.001517547230838]
Ricci curvature is a fundamental concept in differential geometry for encoding local geometric structure.<n>We propose Sobolev-Ricci Curvature (SRC), a graph Ricci curvature induced by Sobolev transport geometry.
arXiv Detail & Related papers (2026-03-13T04:50:36Z)
Curved representational Bregman divergences and their applications [7.070726553564701]
We show that the barycenter of a finite weighted set of parameters under a curved Bregman divergence amounts to the right Bregman projection onto the nonlinear subspace of the barycenter.<n>As an application, we report an efficient method to calculate the intersection of a finite set of $alpha$-divergence spheres.
arXiv Detail & Related papers (2025-04-08T04:05:12Z)
Spectro-Riemannian Graph Neural Networks [39.901731107377095]
Cusp Laplacian is an extension of the traditional graph Laplacian based on Ollivier-Ricci curvature.<n>Cusp Pooling is a hierarchical attention mechanism combined with a curvature-based positional encoding.
arXiv Detail & Related papers (2025-02-01T11:31:01Z)
Ironing the Graphs: Toward a Correct Geometric Analysis of Large-Scale Graphs [2.2557806157585834]
We argue that the classical embedding techniques cannot lead to correct geometric interpretation as they miss the curvature at each point, of manifold. We present an embedding approach, the discrete Ricci flow graph embedding (dRfge) based on the discrete Ricci flow. A major contribution of this paper is that for the first time, we prove the convergence of discrete Ricci flow to a constant curvature and stable distance metrics over the edges.
arXiv Detail & Related papers (2024-07-31T13:47:53Z)
Revealing Decurve Flows for Generalized Graph Propagation [108.80758541147418]
This study addresses the limitations of the traditional analysis of message-passing, central to graph learning, by defining em textbfgeneralized propagation with directed and weighted graphs. We include a preliminary exploration of learned propagation patterns in datasets, a first in the field.
arXiv Detail & Related papers (2024-02-13T14:13:17Z)
DeepRicci: Self-supervised Graph Structure-Feature Co-Refinement for Alleviating Over-squashing [72.70197960100677]
Graph Structure Learning (GSL) plays an important role in boosting Graph Neural Networks (GNNs) with a refined graph. GSL solutions usually focus on structure refinement with task-specific supervision (i.e., node classification) or overlook the inherent weakness of GNNs themselves. We propose to study self-supervised graph structure-feature co-refinement for effectively alleviating the issue of over-squashing in typical GNNs.
arXiv Detail & Related papers (2024-01-23T14:06:08Z)
Predicting Spine Geometry and Scoliosis from DXA Scans [49.68543422441626]
We first train a neural network to predict the middle spine curve in the scan, and then use an integral-based method to determine the curvature along the spine curve. We show that the maximum curvature can be used as a scoring function for ordering the severity of spinal deformation.
arXiv Detail & Related papers (2023-11-15T22:49:08Z)
Continuum Limits of Ollivier's Ricci Curvature on data clouds: pointwise consistency and global lower bounds [1.1126342180866644]
We study the relationship between the curvature of a random geometric graph built from $X$ and the curvature of the manifold $M$ via continuum limits of Ollivier's discrete Ricci curvature. We discuss applications of the global discrete curvature bounds to contraction properties of heat kernels on graphs, as well as implications for manifold learning from data clouds.
arXiv Detail & Related papers (2023-07-05T15:45:53Z)
Curvature-Independent Last-Iterate Convergence for Games on Riemannian Manifolds [77.4346324549323]
We show that a step size agnostic to the curvature of the manifold achieves a curvature-independent and linear last-iterate convergence rate. To the best of our knowledge, the possibility of curvature-independent rates and/or last-iterate convergence has not been considered before.
arXiv Detail & Related papers (2023-06-29T01:20:44Z)
Learning Discretized Neural Networks under Ricci Flow [48.47315844022283]
We study Discretized Neural Networks (DNNs) composed of low-precision weights and activations.<n>DNNs suffer from either infinite or zero gradients due to the non-differentiable discrete function during training.
arXiv Detail & Related papers (2023-02-07T10:51:53Z)
Shape And Structure Preserving Differential Privacy [70.08490462870144]
We show how the gradient of the squared distance function offers better control over sensitivity than the Laplace mechanism. We also show how using the gradient of the squared distance function offers better control over sensitivity than the Laplace mechanism.
arXiv Detail & Related papers (2022-09-21T18:14:38Z)
LTB curves with Lipschitz turn are par-regular [0.0]
This report defines the class of par-regular curves inside the class of locally turn-bounded curves. We prove the converse assertion : locally turn-bounded curves with Lipschitz turn are par-regular.
arXiv Detail & Related papers (2021-12-15T10:10:07Z)
Ricci curvature of quantum channels on non-commutative transportation metric spaces [17.21921346541951]
We introduce the coarse Ricci curvature of a quantum channel as the contraction of non-commutative metrics on the state space. We prove that the coarse Ricci curvature lower bound and its dual gradient estimate, under suitable assumptions, imply the Poincar'e inequality and transportation cost inequalities.
arXiv Detail & Related papers (2021-08-24T09:52:29Z)
Differentiating through the Fr\'echet Mean [51.32291896926807]
Fr'echet mean is a generalization of the Euclidean mean. We show how to differentiate through the Fr'echet mean for arbitrary Riemannian manifold. This fully integrates the Fr'echet mean into the hyperbolic neural network pipeline.
arXiv Detail & Related papers (2020-02-29T19:49:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.