paper-with-me

홈 › Papers

Riemannian Geometry Approach for Minimizing Distortion and its Applications

2022-07-25 · Dror Ozeri

Given an affine transformation $T$, we define its Fisher distortion $Dist_F(T)$. We show that the Fisher distortion has Riemannian metric structure and provide an algorithm for finding mean distorting transformation -- namely -- for a given set $\{T_{i}\}_{i=1}^N$ of affine transformations, find an affine transformation $T$ that minimize the overall distortion $\sum_{i=1}^NDist_F^{2}(T^{-1}T_{i}).$ The mean distorting transformation can be useful in some fields -- in particular, we apply it for rendering affine panoramas.

📄 PDF Abstract BibTeX arXiv:2207.12038

Code (1)

dozeri83/mean_pos_def 공식 구현

Similar Papers 제목 키워드 기반

Riemannian Stochastic Approximation for Minimizing Tame Nonsmooth Objective Functions

2023-02-01 · Johannes Aspman, Vyacheslav Kungurtsev, Reza Roohi Seraji

In many learning applications, the parameters in a model are structurally constrained in a way that can be modeled as them lying on a Riemannian manifold. Riemannian optimization, wherein procedures to enforce an iterati…

Riemannian optimization

Understanding Riemannian Acceleration via a Proximal Extragradient Framework

2021-11-04 · Jikai Jin, Suvrit Sra

We contribute to advancing the understanding of Riemannian accelerated gradient methods. In particular, we revisit Accelerated Hybrid Proximal Extragradient(A-HPE), a powerful framework for obtaining Euclidean accelerate…

Riemannian optimization

Isometric Immersion Learning with Riemannian Geometry

2024-09-23 · Zihao Chen, Wenyong Wang, Yu Xiang

Manifold learning has been proven to be an effective method for capturing the implicitly intrinsic structure of non-Euclidean data, in which one of the primary challenges is how to maintain the distortion-free (isometry)…

Gradient Flows and Riemannian Structure in the Gromov-Wasserstein Geometry

2024-07-16 · Zhengxin Zhang, Ziv Goldfeld, Kristjan Greenewald, Youssef Mroueh 외

The Wasserstein space of probability measures is known for its intricate Riemannian structure, which underpins the Wasserstein geometry and enables gradient flow algorithms. However, the Wasserstein geometry may not be s…

Follow the Energy, Find the Path: Riemannian Metrics from Energy-Based Models

2025-05-23 · Louis Béthune, David Vigouroux, Yilun Du, Rufin VanRullen 외

What is the shortest path between two data points lying in a high-dimensional space? While the answer is trivial in Euclidean geometry, it becomes significantly more complex when the data lies on a curved manifold -- req…