On the smallest possible dimension and the largest possible margin of linear arrangements representing given concept classes

Authors:
Jürgen Forster;Hans Ulrich Simon
Affiliations:
Fakultät für Mathematik, Ruhr-Universität Bochum, Bochum, Germany;Fakultät für Mathematik, Ruhr-Universität Bochum, Bochum, Germany
Venue:
Theoretical Computer Science - Algorithmic learning theory(ALT 2002)
Year:
2006

Citing 10
Cited 7

Matrix analysis

Matrix analysis
Probabilistic communication complexity

Journal of Computer and System Sciences
Topics in matrix analysis

Topics in matrix analysis
The Johnson-Lindenstrauss Lemma and the sphericity of some graphs

Journal of Combinatorial Theory Series A
A training algorithm for optimal margin classifiers

COLT '92 Proceedings of the fifth annual workshop on Computational learning theory
An introduction to support Vector Machines: and other kernel-based learning methods

An introduction to support Vector Machines: and other kernel-based learning methods
Spectral methods for matrix rigidity with applications to size-depth tradeoffs and communication complexity

FOCS '95 Proceedings of the 36th Annual Symposium on Foundations of Computer Science
An Algorithmic Theory of Learning: Robust Concepts and Random Projection

FOCS '99 Proceedings of the 40th Annual Symposium on Foundations of Computer Science
A Linear Lower Bound on the Unbounded Error Probabilistic Communication Complexity

CCC '01 Proceedings of the 16th Annual Conference on Computational Complexity
Limitations of learning via embeddings in euclidean half spaces

The Journal of Machine Learning Research

Halfspace Matrices

Computational Complexity
Learning complexity vs communication complexity

Combinatorics, Probability and Computing
Complexity Lower Bounds using Linear Algebra

Foundations and Trends® in Theoretical Computer Science
A lower bound for agnostically learning disjunctions

COLT'07 Proceedings of the 20th annual conference on Learning theory
Unbounded-error classical and quantum communication complexity

ISAAC'07 Proceedings of the 18th international conference on Algorithms and computation
The Sign-Rank of AC$^0$

SIAM Journal on Computing
Unbounded-error one-way classical and quantum communication complexity

ICALP'07 Proceedings of the 34th international conference on Automata, Languages and Programming

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper discusses theoretical limitations of classification systems that are based on feature maps and use a separating hyperplane in the feature space. In particular, we study the embeddability of a given concept class into a class of Euclidean half spaces of low dimension, or of arbitrarily large dimension but realizing a large margin. New bounds on the smallest possible dimension or on the largest possible margin are presented. In addition, we present new results on the rigidity of matrices and briefly mention applications in complexity and learning theory.