Simplex-Structured Matrix Factorization: Sparsity-based Identifiability and Provably Correct Algorithms

• URL: http://arxiv.org/abs/2007.11446v1
• Date: Wed, 22 Jul 2020 14:01:58 GMT
• Title: Simplex-Structured Matrix Factorization: Sparsity-based Identifiability and Provably Correct Algorithms
• Authors: Maryam Abdolali, Nicolas Gillis
• Abstract summary: We provide novel algorithms with identifiability guarantees for simplex-structured matrix factorization. We illustrate the effectiveness of our approach on synthetic data sets and hyperspectral images.
• Score: 21.737226432466496
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this paper, we provide novel algorithms with identifiability guarantees for simplex-structured matrix factorization (SSMF), a generalization of nonnegative matrix factorization. Current state-of-the-art algorithms that provide identifiability results for SSMF rely on the sufficiently scattered condition (SSC) which requires the data points to be well spread within the convex hull of the basis vectors. The conditions under which our proposed algorithms recover the unique decomposition is in most cases much weaker than the SSC. We only require to have $d$ points on each facet of the convex hull of the basis vectors whose dimension is $d-1$. The key idea is based on extracting facets containing the largest number of points. We illustrate the effectiveness of our approach on synthetic data sets and hyperspectral images, showing that it outperforms state-of-the-art SSMF algorithms as it is able to handle higher noise levels, rank deficient matrices, outliers, and input data that highly violates the SSC.

Related papers

• Tailed Low-Rank Matrix Factorization for Similarity Matrix Completion [14.542166904874147]
  Similarity Completion Matrix serves as a fundamental tool at the core of numerous machinelearning tasks. To address this issue, Similarity Matrix Theoretical (SMC) methods have been proposed, but they suffer complexity. We present two novel, scalable, and effective algorithms, which investigate the PSD property to guide the estimation process and incorporate non low-rank regularizer to ensure the low-rank solution.
  arXiv  Detail & Related papers  (2024-09-29T04:27:23Z)
• Exponentially Convergent Algorithms for Supervised Matrix Factorization [2.1485350418225244]
  Supervised factorization (SMF) is a machine learning method that converges extraction and classification tasks. Our paper provides a novel framework that 'lifts' SMF as a low-rank estimation problem in a combined factor space estimation.
  arXiv  Detail & Related papers  (2023-11-18T23:24:02Z)
• Spectral Entry-wise Matrix Estimation for Low-Rank Reinforcement Learning [53.445068584013896]
  We study matrix estimation problems arising in reinforcement learning (RL) with low-rank structure. In low-rank bandits, the matrix to be recovered specifies the expected arm rewards, and for low-rank Markov Decision Processes (MDPs), it may for example characterize the transition kernel of the MDP. We show that simple spectral-based matrix estimation approaches efficiently recover the singular subspaces of the matrix and exhibit nearly-minimal entry-wise error.
  arXiv  Detail & Related papers  (2023-10-10T17:06:41Z)
• Deep Unrolling for Nonconvex Robust Principal Component Analysis [75.32013242448151]
  We design algorithms for Robust Component Analysis (A) It consists in decomposing a matrix into the sum of a low Principaled matrix and a sparse Principaled matrix.
  arXiv  Detail & Related papers  (2023-07-12T03:48:26Z)
• Statistically Optimal K-means Clustering via Nonnegative Low-rank Semidefinite Programming [25.210724274471914]
  $K$-means clustering is a widely used machine learning method for identifying patterns in large datasets. In this paper, we consider an NMF-like algorithm that solves nonnegative low-rank $K$-means factorization problem. Our algorithm achieves significantly smaller mis-clustering errors compared to the existing state-the-art while maintaining scalability.
  arXiv  Detail & Related papers  (2023-05-29T00:39:55Z)
• Exploring the Algorithm-Dependent Generalization of AUPRC Optimization with List Stability [107.65337427333064]
  optimization of the Area Under the Precision-Recall Curve (AUPRC) is a crucial problem for machine learning. In this work, we present the first trial in the single-dependent generalization of AUPRC optimization. Experiments on three image retrieval datasets on speak to the effectiveness and soundness of our framework.
  arXiv  Detail & Related papers  (2022-09-27T09:06:37Z)
• Self-supervised Symmetric Nonnegative Matrix Factorization [82.59905231819685]
  Symmetric nonnegative factor matrix (SNMF) has demonstrated to be a powerful method for data clustering. Inspired by ensemble clustering that aims to seek better clustering results, we propose self-supervised SNMF (S$3$NMF) We take advantage of the sensitivity to code characteristic of SNMF, without relying on any additional information.
  arXiv  Detail & Related papers  (2021-03-02T12:47:40Z)
• Sparse PCA via $l_{2,p}$-Norm Regularization for Unsupervised Feature Selection [138.97647716793333]
  We propose a simple and efficient unsupervised feature selection method, by combining reconstruction error with $l_2,p$-norm regularization. We present an efficient optimization algorithm to solve the proposed unsupervised model, and analyse the convergence and computational complexity of the algorithm theoretically.
  arXiv  Detail & Related papers  (2020-12-29T04:08:38Z)
• Sparse PCA: Algorithms, Adversarial Perturbations and Certificates [9.348107805982604]
  We study efficient algorithms for Sparse PCA in standard statistical models. Our goal is to achieve optimal recovery guarantees while being resilient to small perturbations.
  arXiv  Detail & Related papers  (2020-11-12T18:58:51Z)
• Optimal Randomized First-Order Methods for Least-Squares Problems [56.05635751529922]
  This class of algorithms encompasses several randomized methods among the fastest solvers for least-squares problems. We focus on two classical embeddings, namely, Gaussian projections and subsampled Hadamard transforms. Our resulting algorithm yields the best complexity known for solving least-squares problems with no condition number dependence.
  arXiv  Detail & Related papers  (2020-02-21T17:45:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.