Entropy numbers of embeddings of Schatten classes
نویسندگان
چکیده
منابع مشابه
Entropy Numbers of Linear Function Classes
This paper collects together a miscellany of results originally motivated by the analysis of the generalization performance of the “maximum-margin” algorithm due to Vapnik and others. The key feature of the paper is its operator-theoretic viewpoint. New bounds on covering numbers for classes related to Maximum Margin classes are derived directly without making use of a combinatorial dimension s...
متن کاملEntropy numbers of embeddings of some 2-microlocal Besov spaces
We investigate compactness and asymptotic behaviour of the entropy numbers of embeddings B s1,s1 p1,q1 (R, U) ↪→ B s2,s2 p2,q2 (R, U) . Here B ′ p,q (Rn, U) denotes a 2-microlocal Besov space with a weight given by the distance to a fixed set U ⊂ Rn.
متن کاملEntropy Numbers of Embeddings of Weighted Besov Spaces
We investigate the asymptotic behavior of the entropy numbers of the compact embedding B1 p1,q1(R d , α) ↪→ B2 p2,q2(R ). Here Bs p,q (R d , α) denotes a weighted Besov space, where the weight is given by wα(x) = (1 + |x |2)α/2, and B2 p2,q2 (Rd ) denotes the unweighted Besov space, respectively. We shall concentrate on the so-called limiting situation given by the following constellation of pa...
متن کاملLow Regularity Classes and Entropy Numbers
We note a sharp embedding of the Besov space B∞ 0,q(T) into exponential classes and prove entropy estimates for the compact embedding of subclasses with logarithmic smoothness, considered by Kashin and Temlyakov.
متن کاملEmbeddings of Schatten Norms with Applications to Data Streams
Given an n×d matrix A, its Schatten-p norm, p ≥ 1, is defined as ‖A‖p = (∑rank(A) i=1 σi(A) p )1/p , where σi(A) is the i-th largest singular value of A. These norms have been studied in functional analysis in the context of non-commutative `p-spaces, and recently in data stream and linear sketching models of computation. Basic questions on the relations between these norms, such as their embed...
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: Journal of Functional Analysis
سال: 2017
ISSN: 0022-1236
DOI: 10.1016/j.jfa.2017.08.008