On Riemannian Optimization over Positive Definite Matrices with the Bures-Wasserstein Geometry
Dec 6, 2021
Speakers
Bamdev Mishra
Sprecher:in · 0 Follower:innen
Pratik Kumar Jawanpuria
Sprecher:in · 0 Follower:innen
Junbin Gao
Sprecher:in · 0 Follower:innen
About
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…
Organizer
NeurIPS 2021
Konto · 1,9k Follower:innen
About 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.
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Diversity is All You Need to Improve Bayesian Model Averaging
Später ansehen
Ewigspeicher-Fortschrittswert: 0 = 0.0%
Scalable Intervention Target Estimation in Linear Models
Später ansehen
Burak Varici, …
Ewigspeicher-Fortschrittswert: 0 = 0.0%
Adversarial Robustness of Streaming Algorithms through Importance Sampling
Später ansehen
Ewigspeicher-Fortschrittswert: 0 = 0.0%
Capacity and Bias of Learned Geometric Embeddings for Directed Graphs
Später ansehen
Ewigspeicher-Fortschrittswert: 0 = 0.0%
Channel Permutations for N:M Sparsity
Später ansehen
Jeff Pool, …
Ewigspeicher-Fortschrittswert: 1 = 0.1%
Annotation Quality Framework - Accuracy,Credibility, and Consistency
Später ansehen
Ewigspeicher-Fortschrittswert: 0 = 0.0%