Random Projections for Non - Negative Matrix
نویسنده
چکیده
Non-negative matrix factorization (NMF) is a widely used tool for exploratory data analysis in many disciplines. In this paper, we describe an approach to NMF based on random projections and give a geometric analysis of a prototypical algorithm. Our main result shows the proto-algorithm requires κ̄k log k optimizations to find all the extreme columns of the matrix, where k is the number of extreme columns, and κ̄ is a geometric condition number. We show empirically that the proto-algorithm is robust to noise and well-suited to modern distributed computing architectures.
منابع مشابه
Machine Learning and Non-Negative Compressive Sampling
The new emerging theory of compressive sampling demonstrates that by exploiting the structure of a signal, it is possible to sample a signal below the Nyquist rate—using random projections—and achieve perfect reconstruction. In this paper, we consider a special case of compressive sampling where the uncompressed signal is non-negative, and propose a number of sparse recovery algorithms—which ut...
متن کاملAttenuation Correction in SPECT during Image Reconstruction using an Inverse Monte Carlo Method: A Simulation Study
Introduction: The main goal of SPECT imaging is to determine activity distribution inside the organs of the body. However, due to photon attenuation, it is almost impossible to do a quantitative study. In this paper, we suggest a mathematical relationship between activity distribution and its corresponding projections using a transfer matrix. Monte Carlo simulation was used to find a precise tr...
متن کاملOn Approximating the Lp Distances for p>2
Many applications in machine learning and data mining require computing pairwise lp distances in a data matrix A ∈ R . For massive high-dimensional data, computing all pairwise distances of A can be infeasible. In fact, even storing A or all pairwise distances of A in the memory may be also infeasible. For 0 < p ≤ 2, efficient small space algorithms exist, for example, based on the method of st...
متن کاملIterative Weighted Non-smooth Non-negative Matrix Factorization for Face Recognition
Non-negative Matrix Factorization (NMF) is a part-based image representation method. It comes from the intuitive idea that entire face image can be constructed by combining several parts. In this paper, we propose a framework for face recognition by finding localized, part-based representations, denoted “Iterative weighted non-smooth non-negative matrix factorization” (IWNS-NMF). A new cost fun...
متن کاملEfficient Nonnegative Matrix Factorization with Random Projections
The recent years have witnessed a surge of interests in Nonnegative Matrix Factorization (NMF) in data mining and machine learning fields. Despite its elegant theory and empirical success, one of the limitations of NMF based algorithms is that it needs to store the whole data matrix in the entire process, which requires expensive storage and computation costs when the data set is large and high...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2014