Theory of Classification: a Survey of Some Recent Advances Page 1 ESAIM: PS ESAIM:
Probability and Statistics November 2005, Vol. 9, p. 323–375 DOI: 10.1051/ps:2005018 …

The remarkable practical success of deep learning has revealed some major surprises from
a theoretical perspective. In particular, simple gradient methods easily find near-optimal …

Deep learning (DL) has emerged as an effective tool for channel estimation in wireless
communication systems, especially under some imperfect environments. However, even …

Weak Convergence Page 1 1.3 Weak Convergence In this section IDl and IE are metric spaces
with metrics d and e, respectively. The set of all continuous, bounded functions f: IDl 1--+ IR is …

The regression estimation problem has a long history. Already in 1632 Galileo Galilei used a
procedure which can be interpreted as? tting a linear relationship to contaminated observed …

The theory of empirical processes provides valuable tools for the development of asymptotic
theory in (nonparametric) statistical models, and makes it possible to give a unified treatment …

We introduce a family of adaptive estimators on graphs, based on penalizing the l 1 norm of
discrete graph differences. This generalizes the idea of trend filtering (Kim et al., 2009; …

This paper studies the fundamental dimensionality of synchrophasor data, and proposes an
online application for early event detection using the reduced dimensionality. First, the …

Information-Theoretic Determination of Minimax Rates of Convergence Page 1 The Annals
of Statistics 1999, Vol. 27, No. 5, 1564-1599 INFORMATION-THEORETIC …

Performance bounds for criteria for model selection are developed using recent theory for
sieves. The model selection criteria are based on an empirical loss or contrast function with …