A Riemannian gossip approach to subspace learning on Grassmann manifold
In this paper, we focus on subspace learning problems on the Grassmann manifold. Interesting applications in this setting include low-rank matrix completion and low-dimensional multivariate regression, among others. Motivated by privacy concerns, we aim to solve such problems in a decentralized setting where multiple agents have access to (and solve) only a part of the whole optimization problem. The agents communicate with each other to arrive at a consensus, i.e., agree on a common quantity, via the gossip protocol. We propose a novel cost function for subspace learning on the Grassmann manifold, which is a weighted sum of several sub-problems (each solved by an agent) and the communication cost among the agents. The cost function has a finite sum structure. In the proposed modeling approach, different agents learn individual local subspace but they achieve asymptotic consensus on the global learned subspace. The approach is scalable and parallelizable. Numerical experiments show the efficacy of the proposed decentralized algorithms on various matrix completion and multivariate regression benchmarks.
Code (0)
등록된 구현이 없습니다.
Tasks
Low-Rank Matrix CompletionMatrix CompletionregressionSimilar Papers 제목 키워드 기반
A Riemannian gossip approach to decentralized matrix completion
In this paper, we propose novel gossip algorithms for the low-rank decentralized matrix completion problem. The proposed approach is on the Riemannian Grassmann manifold that allows local matrix completion by different a…
Matrix CompletionDimensionality Reduction on Grassmannian via Riemannian Optimization: A Generalized Perspective
This paper proposes a generalized framework with joint normalization which learns lower-dimensional subspaces with maximum discriminative power by making use of the Riemannian geometry. In particular, we model the simila…
Dimensionality ReductionRiemannian optimizationDifferential Evolution for Grassmann Manifold Optimization: A Projection Approach
We propose a novel evolutionary algorithm for optimizing real-valued objective functions defined on the Grassmann manifold Gr}(k,n), the space of all k-dimensional linear subspaces of R^n. While existing optimization tec…
Riemannian optimizationCartan flow matching
We introduce Cartan flow matching, a general framework for training flow matching models on Riemannian symmetric spaces, i.e. Riemannian manifolds with the property that at any point there exists a geodesic symmetry. Thi…
Extrinsic Methods for Coding and Dictionary Learning on Grassmann Manifolds
Sparsity-based representations have recently led to notable results in various visual recognition tasks. In a separate line of research, Riemannian manifolds have been shown useful for dealing with features and models th…
Action RecognitionClassificationDictionary LearningFace Recognition+4