Optimal dictionary for least squares representation

Authors Mohammed Rayyan Sheriff, Debasish Chatterjee

Publication date 17 April 2018

Full work available at URL https://arxiv.org/abs/1603.02074, http://jmlr.csail.mit.edu/papers/v18/16-046.html

\(\ell_2\)-optimal dictionary finite tight frames rank-1 decomposition

Conditioning of matrices (15A12) Applications of functional analysis in optimization, convex analysis, mathematical programming, economics (46N10) Linear optimal control problems (49N05) Learning and adaptive systems in artificial intelligence (68T05)

Abstract: Dictionaries are collections of vectors used for representations of random vectors in Euclidean spaces. Recent research on optimal dictionaries is focused on constructing dictionaries that offer sparse representations, i.e.,

e l l_{0}

-optimal representations. Here we consider the problem of finding optimal dictionaries with which representations of samples of a random vector are optimal in an

e l l_{2}

-sense: optimality of representation is defined as attaining the minimal average

e l l_{2}

-norm of the coefficients used to represent the random vector. With the help of recent results on rank-

1

decompositions of symmetric positive semidefinite matrices, we provide an explicit description of

e l l_{2}

-optimal dictionaries as well as their algorithmic constructions in polynomial time.

Recommendations

Cites work

Cited in

(5)

This page was built for publication: Optimal dictionary for least squares representation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4637030)