A subgaussian embedding theorem
نویسندگان
چکیده
We prove a subgaussian extension of a Gaussian result on embedding subsets of a Euclidean space into normed spaces. Using the concentration of a random subgaussian vector around its mean we obtain an isomorphic (rather than almost isometric) result, under an additional cotype assumption on the normed space considered.
منابع مشابه
Non-Asymptotic Theory of Random Matrices Lecture 18: Strong invertibility of subgaussian matrices and Small ball probability via arithmetic progression
1 Strong invertibility of subgaussian matrices In the last lecture, we derived an estimate for the smallest singular value of a subgaussian random matrix; Theorem 1. Let A be a n × n subgaussian matrix. Then, for any > 0, P(s n (A) < ε √ n) ≤ cε + Cn −1 2 (1) In particular, this implies s n (A) ∼ 1 √ n with high probability. However, (1) cannot show P(s n (A) < ε √ n) → 0 as → 0 because of the ...
متن کاملSubgaussian random variables, Hoeffding’s inequality, and Cramér’s large deviation theorem
متن کامل
Embedding normed linear spaces into $C(X)$
It is well known that every (real or complex) normed linear space $L$ is isometrically embeddable into $C(X)$ for some compact Hausdorff space $X$. Here $X$ is the closed unit ball of $L^*$ (the set of all continuous scalar-valued linear mappings on $L$) endowed with the weak$^*$ topology, which is compact by the Banach--Alaoglu theorem. We prove that the compact Hausdorff space $X$ can ...
متن کاملTowards a Constructive Version of Banaszczyk's Vector Balancing Theorem
An important theorem of Banaszczyk (Random Structures & Algorithms ‘98) states that for any sequence of vectors of `2 norm at most 1/5 and any convex body K of Gaussian measure 1/2 in R, there exists a signed combination of these vectors which lands inside K. A major open problem is to devise a constructive version of Banaszczyk’s vector balancing theorem, i.e. to find an efficient algorithm wh...
متن کاملDimensionality reduction with subgaussian matrices: a unified theory
We present a theory for Euclidean dimensionality reduction with subgaussian matrices which unifies several restricted isometry property and Johnson-Lindenstrauss type results obtained earlier for specific data sets. In particular, we recover and, in several cases, improve results for sets of sparse and structured sparse vectors, low-rank matrices and tensors, and smooth manifolds. In addition, ...
متن کامل