On Riemannian Optimization over Positive Definite Matrices with the Bures-Wasserstein Geometry
6. prosince 2021
Řečníci
Bamdev Mishra
Řečník · 0 sledujících
Pratik Kumar Jawanpuria
Řečník · 0 sledujících
Junbin Gao
Řečník · 0 sledujících
O prezentaci
In this paper, we comparatively analyze the Bures-Wasserstein (BW) geometry with the popular Affine-Invariant (AI) geometry for Riemannian optimization on the symmetric positive definite (SPD) matrix manifold. Our study begins with an observation that the BW metric has a linear dependence on SPD matrices in contrast to the quadratic dependence of the AI metric. We build on this to show that the BW metric is a more suitable and robust choice for several Riemannian optimization problems over ill-conditioned SPD matrices. We show that the BW geometry has a non-negative curvature, which further improves convergence rates of algorithms over the non-positively curved AI geometry. Finally, we verify that several popular cost functions, which are known to be geodesic convex under the AI geometry, are also geodesic convex under the BW geometry. Extensive experiments on various applications support our findings.In this paper, we comparatively analyze the Bures-Wasserstein (BW) geometry with the popular Affine-Invariant (AI) geometry for Riemannian optimization on the symmetric positive definite (SPD) matrix manifold. Our study begins with an observation that the BW metric has a linear dependence on SPD matrices in contrast to the quadratic dependence of the AI metric. We build on this to show that the BW metric is a more suitable and robust choice for several Riemannian optimization problems over ill-c…
Organizátor
NeurIPS 2021
Účet · 1,9k sledujících
O organizátorovi (NeurIPS 2021)
Neural Information Processing Systems (NeurIPS) is a multi-track machine learning and computational neuroscience conference that includes invited talks, demonstrations, symposia and oral and poster presentations of refereed papers. Following the conference, there are workshops which provide a less formal setting.
Baví vás formát? Nechte SlidesLive zachytit svou akci!
Profesionální natáčení a streamování po celém světě.
Sdílení
Doporučená videa
Prezentace na podobné téma, kategorii nebo přednášejícího
ARKitScenes - A Diverse Real-World Dataset for 3D Indoor Scene Understanding Using Mobile RGB-D Data
Zhlédnout později
Gilad Baruch, …
Pro uložení prezentace do věčného trezoru hlasovalo 0 diváků, což je 0.0 %
ImageBART: Bidirectional Context with Multinomial Diffusion for Autoregressive Image Synthesis
Zhlédnout později
Pro uložení prezentace do věčného trezoru hlasovalo 0 diváků, což je 0.0 %
From the geometry of high dimensional energy landscapes to optimal annealing in a dissipative many body quantum optimizer
Zhlédnout později
Pro uložení prezentace do věčného trezoru hlasovalo 0 diváků, což je 0.0 %
A Geometric Perspective towards Neural Calibration via Sensitivity Decomposition
Zhlédnout později
Junjiao Tian, …
Pro uložení prezentace do věčného trezoru hlasovalo 0 diváků, což je 0.0 %
Multiwavelet-based Operator Learning for Differential Equations
Zhlédnout později
Gaurav Gupta, …
Pro uložení prezentace do věčného trezoru hlasovalo 0 diváků, což je 0.0 %
Panel Discussion
Zhlédnout později
Jo Boaler, …
Pro uložení prezentace do věčného trezoru hlasovalo 0 diváků, což je 0.0 %