Rescaled pure greedy algorithm for Hilbert and Banach spaces

DOI10.1016/J.ACHA.2015.10.008MaRDI QIDQ326773zbMATH OpenOpenAlexFDO

Authors Guergana Petrova

Publication date 12 October 2016

Published in Applied and Computational Harmonic Analysis (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1505.03604

zbMATH Keywords

greedy algorithmsrates of convergence

Mathematics Subject Classification ID

Rate of convergence, degree of approximation (41A25) Approximation by arbitrary nonlinear expressions; widths and entropy (41A46)

Abstract: We show that a very simple modification of the Pure Greedy Algorithm for approximating functions by sparse sums from a dictionary in a Hilbert or more generally a Banach space has optimal convergence rates on the class of convex combinations of dictionary elements

Recommendations

• Greedy algorithms in Banach spaces
• Rescaled pure greedy algorithm for convex optimization
• Greedy algorithms for reduced bases in Banach spaces
• Greedy approximation in Banach spaces
• Simultaneous greedy approximation in Banach spaces
• Greedy algorithms and approximation properties for frames in Hilbert spaces
• Greedy algorithms and bases from the point of view of Banach space theory
• Greedy algorithms and Kolmogorov widths in Banach spaces
• Convergence of greedy algorithms in Banach spaces
• Greedy-type approximation in Banach spaces and applications

Cites work

• A simple lemma on greedy approximation in Hilbert space and convergence rates for projection pursuit regression and neural network training
• Approximate weak greedy algorithms
• Approximation and learning by greedy algorithms
• Efficient agnostic learning of neural networks with bounded fan-in
• Greedy approximation
• Greedy strategies for convex optimization
• Lower bounds for the rate of convergence of greedy algorithms
• On a conjecture of Huber concerning the convergence of projection pursuit regression
• On the rate of convergence of greedy algorithms.
• Rate of convergence of pure greedy algorithm.
• Rates of convex approximation in non-Hilbert spaces
• Rescaled pure greedy algorithm for convex optimization
• Some remarks on greedy algorithms
• Two lower estimates in greedy approximation
• Universal approximation bounds for superpositions of a sigmoidal function
• Weak greedy algorithms

Cited in

(9)

• Efficiency of the weak Rescaled Pure Greedy Algorithm
• Entropy-based convergence rates of greedy algorithms
• On the rate of convergence of a pure greedy algorithm.
• Optimality of the rescaled pure greedy learning algorithms
• A unified way of analyzing some greedy algorithms
• Biorthogonal greedy algorithms in convex optimization
• Rescaled pure greedy algorithm for convex optimization
• Vector greedy algorithms
• Unified error estimate for weak biorthogonal greedy algorithms

This page was built for publication: Rescaled pure greedy algorithm for Hilbert and Banach spaces

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q326773)