• Home
  • Search
  • A PAC Approach to Application-Specific Algorithm Selection
  • Open Access IconOpen Access
  • Cite Icon64
  • https://doi.org/10.1137/15m1050276Copy DOI Icon

A PAC Approach to Application-Specific Algorithm Selection

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

The best algorithm for a computational problem generally depends on the “relevant inputs,” a concept that depends on the application domain and often defies formal articulation. While there is a large body of literature on empirical approaches to selecting the best algorithm for a given application domain, there has been surprisingly little theoretical analysis of the problem. This paper adapts concepts from statistical and online learning theory to reason about application-specific algorithm selection. Our models capture several state-of-the-art empirical and theoretical approaches to the problem, ranging from self-improving algorithms to empirical performance models, and our results identify conditions under which these approaches are guaranteed to perform well. We present one framework that models algorithm selection as a statistical learning problem, and our work here shows that dimension notions from statistical learning theory, historically used to measure the complexity of classes of binary- and re...

Similar Papers
  • Research Article
  • Citations10

Testability and Ockham’s Razor: How Formal and Statistical Learning Theory Converge in the New Riddle of Induction

  • Aug 07, 2009
  • Journal of Philosophical Logic
  • Daniel Steel
  • Research Article
  • Citations3

Shearlet-based regularization in statistical inverse learning with an application to x-ray tomography

  • Apr 11, 2022
  • Inverse Problems
  • Tatiana A Bubba +1
  • Conference Article
  • Citations34

Complexity measures in Genetic Programming learning: A brief review

  • Jul 01, 2016
  • Nam Le +3
  • Conference Article
  • Citations3

Statistical learning and VC theory

  • May 06, 2001
  • P Bartlett
  • Research Article

A Co-Evolutionary Computing for Statistical Learning Theory

  • Dec 01, 2005
  • International Journal of Fuzzy Logic and Intelligent Systems
  • Sung-Hae Jun
  • Supplementary Content

Predicting Brain Morphogenesis via Physics-Transfer Learning

  • Feb 09, 2026
  • Research Square
  • Zhiping Xu +3
  • Research Article
  • Citations2

Applying statistical learning theory to deep learning

  • Oct 30, 2024
  • Journal of Statistical Mechanics: Theory and Experiment
  • Cédric Gerbelot +5
  • Book Chapter
  • Citations1

Statistical Learning in Control and Matrix Theory

  • Jan 01, 1998
  • M. Vidyasagar
  • Conference Article
  • Citations1

Statistical learning controller for the energy management in a fuel cell electric vehicle

  • Jan 01, 2008
  • M Cavalletti +5
  • PDF
  • Research Article
  • Citations6

Geometric Positioning Accuracy Improvement of ZY-3 Satellite Imagery Based on Statistical Learning Theory.

  • May 24, 2018
  • Sensors
  • Niangang Jiao +4
  • Single Book
  • Citations31

Machine Learning for Signal Processing

  • Aug 13, 2019
  • Max A Little
  • Conference Article

Some Theoretical Studies on Learning Theory with Samples Corrupted by Noise

  • Jan 01, 2006
  • Jun-Hua Li +3
  • Research Article
  • Citations28

On Stochastic Optimization and Statistical Learning in Reproducing Kernel Hilbert Spaces by Support Vector Machines (SVM)

  • Jan 01, 2009
  • Informatica
  • Vladimir Norkin +1
  • Book Chapter
  • Citations3

Kernel-Based Machines for Abstract and Easy Modeling of Automatic Learning

  • Jan 01, 2011
  • Alessandro Moschitti
  • Book Chapter
  • Citations5

β_SVM a new Support Vector Machine kernel

  • Jan 01, 2003
  • Tarek M. Hamdani +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.