Matrix Concentration for Products
نویسندگان
چکیده
This paper develops nonasymptotic growth and concentration bounds for a product of independent random matrices. These results sharpen generalize recent work Henriksen–Ward, they are similar in spirit to the Ahlswede–Winter Tropp sum The argument relies on uniform smoothness properties Schatten trace classes.
منابع مشابه
Matrix Concentration for Expander Walks
We prove a Chernoff-type bound for sums of matrix-valued random variables sampled via a random walk on an expander, confirming a conjecture due to Wigderson and Xiao [WX]. Our proof is based on a new multi-matrix extension of the Golden-Thompson inequality which improves in some ways the inequality in [SBT17] and may be of independent interest, as well as an adaptation of an argument for the sc...
متن کاملMatrix Factorization and Matrix Concentration
Matrix Factorization and Matrix Concentration by Lester Wayne Mackey II Doctor of Philosophy in Electrical Engineering and Computer Sciences with the Designated Emphasis in Communication, Computation, and Statistics University of California, Berkeley Professor Michael I. Jordan, Chair Motivated by the constrained factorization problems of sparse principal components analysis (PCA) for gene expr...
متن کاملEvaluating products of matrix pencils and collapsing matrix products
This paper describes three numerical methods to collapse a formal product of p pairs of matrices P = Q p?1 k=0 E ?1 k A k down to the product of a single pair ^ E ?1 ^ A. In the setting of linear relations, the product formally extends to the case in which some of the E k 's are singular and it is impossible to explicitly form P as a single matrix. The methods diier in op count, work space, and...
متن کاملMatrix Concentration Inequalities
In recent years, random matrices have come to play a major role in computational mathematics, but most of the classical areas of random matrix theory remain the province of experts. Over the last decade, with the advent of matrix concentration inequalities, research has advanced to the point where we can conquer many (formerly) challenging problems with a page or two of arithmetic. The aim of t...
متن کاملAddition Requirements for Matrix and Transposed Matrix Products
Let M be an s ×t matrix and let M T be the transpose of M . Let x and y be t − and s −dimensional indeterminate column vectors, respectively. We show that any linear algorithm A that computes M x has associated with it a natural dual linear algorithm denoted A T that computes M T y . Furthermore, if M has no zero rows or columns then the number of additions used by A T exceeds the number of add...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Foundations of Computational Mathematics
سال: 2021
ISSN: ['1615-3383', '1615-3375']
DOI: https://doi.org/10.1007/s10208-021-09533-9