Rademacher series and decoupling
نویسنده
چکیده
We study decoupling in quasi-Banach spaces. We show that decoupling is permissible in some quasi-Banach spaces (e.g., Lp and Lp/Hp when 0 < p < 1) but fails in other spaces such as the Schatten ideal Sp when 0 < p < 1. We also relate our ideas to a possible extension of the Grothendieck inequality.
منابع مشابه
ZigZag: A New Approach to Adaptive Online Learning
We develop a new family of algorithms for the online learning setting with regret against any data sequence bounded by the empirical Rademacher complexity of that sequence. To develop a general theory of when this type of adaptive regret bound is achievable we establish a connection to the theory of decoupling inequalities for martingales in Banach spaces. When the hypothesis class is a set of ...
متن کاملModerate Deviations for Degenerate U-processes
Su cient conditions for a rank-dependent moderate deviations principle (MDP) for degenerate U -processes are presented. The MDP for VC classes of functions is obtained under exponential moments of the envelope. Among other techniques, randomization, decoupling inequalities and integrability of Gaussian and Rademacher chaos are used to present new Bernstein-type inequalities for U -processes whi...
متن کاملUniform Ergodic Theorems for Dynamical Systems Under VC Entropy Conditions
The classic limit theorems of Vapnik and Chervonenkis [27,28] show that if a function class F satisfies a random entropy condition, then the strong law of large numbers holds uniformly over F . In this paper we show that an analogous weighted entropy condition implies that Birkhoff’s pointwise ergodic theorem holds uniformly over F . In this way we obtain a variety of uniform ergodic theorems f...
متن کاملOn the Generalization Ability of Online Learning Algorithms for Pairwise Loss Functions
In this paper, we study the generalization properties of online learning based stochastic methods for supervised learning problems where the loss function is dependent on more than one training sample (e.g., metric learning, ranking). We present a generic decoupling technique that enables us to provide Rademacher complexity-based generalization error bounds. Our bounds are in general tighter th...
متن کامل1 99 9 the Distribution of Vector - Valued Rademacher Series
Let X = ε n x n be a Rademacher series with vector-valued coefficients. We obtain an approximate formula for the distribution of the random variable ||X|| in terms of its mean and a certain quantity derived from the K-functional of interpolation theory. Several applications of the formula are given. In [6] the second-named author calculated the distribution of a scalar Rademacher series ε n a n...
متن کامل