paper-with-me

홈 › Papers

Geometric Analysis of Nonconvex Optimization Landscapes for Overcomplete Learning

2020-05-01 · ICLR 2020 1 · Qing Qu, Yuexiang Zhai, Xiao Li, Yuqian Zhang, Zhihui Zhu

Learning overcomplete representations finds many applications in machine learning and data analytics. In the past decade, despite the empirical success of heuristic methods, theoretical understandings and explanations of these algorithms are still far from satisfactory. In this work, we provide new theoretical insights for several important representation learning problems: learning (i) sparsely used overcomplete dictionaries and (ii) convolutional dictionaries. We formulate these problems as $\ell^4$-norm optimization problems over the sphere and study the geometric properties of their nonconvex optimization landscapes. For both problems, we show the nonconvex objective has benign (global) geometric structures, which enable the development of efficient optimization methods finding the target solutions. Finally, our theoretical results are justified by numerical simulations.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Representation Learning

Similar Papers 제목 키워드 기반

Analysis of the Optimization Landscapes for Overcomplete Representation Learning

2019-12-05 · Qing Qu, Yuexiang Zhai, Xiao Li, Yuqian Zhang 외

We study nonconvex optimization landscapes for learning overcomplete representations, including learning (i) sparsely used overcomplete dictionaries and (ii) convolutional dictionaries, where these unsupervised learning …

global-optimizationRepresentation Learning

Finding the Sparsest Vectors in a Subspace: Theory, Algorithms, and Applications

2020-01-20 · Qing Qu, Zhihui Zhu, Xiao Li, Manolis C. Tsakiris 외

The problem of finding the sparsest vector (direction) in a low dimensional subspace can be considered as a homogeneous variant of the sparse recovery problem, which finds applications in robust subspace recovery, dictio…

Dictionary LearningRepresentation Learning

From Symmetry to Geometry: Tractable Nonconvex Problems

2020-07-14 · Yuqian Zhang, Qing Qu, John Wright

As science and engineering have become increasingly data-driven, the role of optimization has expanded to touch almost every stage of the data analysis pipeline, from signal and data acquisition to modeling and predictio…

No Spurious Local Minima in Nonconvex Low Rank Problems: A Unified Geometric Analysis

2017-04-03 · ICML 2017 8 · Rong Ge, Chi Jin, Yi Zheng

In this paper we develop a new framework that captures the common landscape underlying the common non-convex low-rank matrix problems including matrix sensing, matrix completion and robust PCA. In particular, we show for…

Matrix Completion

Approximate message passing for nonconvex sparse regularization with stability and asymptotic analysis

2017-11-08 · Ayaka Sakata, Yingying Xu

We analyse a linear regression problem with nonconvex regularization called smoothly clipped absolute deviation (SCAD) under an overcomplete Gaussian basis for Gaussian random data. We propose an approximate message pass…