paper-with-me

Papers

Compressed Subspace Learning Based on Canonical Angle Preserving Property

2019-07-14 · Yuchen Jiao, Gen Li, Yuantao Gu

Union of Subspaces (UoS) is a popular model to describe the underlying low-dimensional structure of data. The fine details of UoS structure can be described in terms of canonical angles (also known as principal angles) between subspaces, which is a well-known characterization for relative subspace positions. In this paper, we prove that random projection with the so-called Johnson-Lindenstrauss (JL) property approximately preserves canonical angles between subspaces with overwhelming probability. This result indicates that random projection approximately preserves the UoS structure. Inspired by this result, we propose a framework of Compressed Subspace Learning (CSL), which enables to extract useful information from the UoS structure of data in a greatly reduced dimension. We demonstrate the effectiveness of CSL in various subspace-related tasks such as subspace visualization, active subspace detection, and subspace clustering.

📄 PDF Abstract BibTeX arXiv:1907.06166

Code (0)

등록된 구현이 없습니다.

Tasks

ClusteringDimensionality Reduction

Similar Papers 제목 키워드 기반

Interpolating Compressed Parameter Subspaces

2022-05-19 · Siddhartha Datta, Nigel Shadbolt

Inspired by recent work on neural subspaces and mode connectivity, we revisit parameter subspace sampling for shifted and/or interpolatable input distributions (instead of a single, unshifted distribution). We enforce a …

Continual Learning

Restricted Isometry Property of Gaussian Random Projection for Finite Set of Subspaces

2017-04-07 · Gen Li, Yuantao Gu

Dimension reduction plays an essential role when decreasing the complexity of solving large-scale problems. The well-known Johnson-Lindenstrauss (JL) Lemma and Restricted Isometry Property (RIP) admit the use of random p…

Clusteringcompressed sensingDimensionality ReductionLEMMA

Subspace Perspective on Canonical Correlation Analysis: Dimension Reduction and Minimax Rates

2016-05-12 · Zhuang Ma, Xiao-Dong Li

Canonical correlation analysis (CCA) is a fundamental statistical tool for exploring the correlation structure between two sets of random variables. In this paper, motivated by recent success of applying CCA to learn low…

Dimensionality ReductionPrediction

MoCaNet: Motion Retargeting in-the-wild via Canonicalization Networks

2021-12-19 · Wentao Zhu, Zhuoqian Yang, Ziang Di, Wayne Wu 외

We present a novel framework that brings the 3D motion retargeting task from controlled environments to in-the-wild scenarios. In particular, our method is capable of retargeting body motion from a character in a 2D mono…

3D ReconstructionAction Analysismotion retargetingRetrieval

Rigorous Restricted Isometry Property of Low-Dimensional Subspaces

2018-01-30 · Gen Li, Qinghua Liu, Yuantao Gu

Dimensionality reduction is in demand to reduce the complexity of solving large-scale problems with data lying in latent low-dimensional structures in machine learning and computer version. Motivated by such need, in thi…

compressed sensingDimensionality ReductionLEMMA