Kernels as features: on kernels, margins, and low-dimensional mappings

DOI10.1007/s10994-006-7550-1zbMath1470.68077OpenAlexW2103164654MaRDI QIDQ851869

Santosh Vempala, Maria-Florina Balcan, Avrim L. Blum

Publication date: 22 November 2006

Published in: Machine Learning (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s10994-006-7550-1

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Computational aspects of data analysis and big data (68T09)

Related Items (17)

Deep learning: a statistical viewpoint ⋮ Generalization error of random feature and kernel methods: hypercontractivity and kernel matrix concentration ⋮ Beam search algorithms for multilabel learning ⋮ Data-independent random projections from the feature-map of the homogeneous polynomial kernel of degree two ⋮ Random Projection and Recovery for High Dimensional Optimization with Arbitrary Outliers ⋮ Parameterized attribute reduction with Gaussian kernel based fuzzy rough sets ⋮ Structure from Randomness in Halfspace Learning with the Zero-One Loss ⋮ Toward a unified theory of sparse dimensionality reduction in Euclidean space ⋮ Unnamed Item ⋮ Adaptive metric dimensionality reduction ⋮ MREKLM: a fast multiple empirical kernel learning machine ⋮ A theory of learning with similarity functions ⋮ Theory and Algorithm for Learning with Dissimilarity Functions ⋮ Sparse Learning for Large-Scale and High-Dimensional Data: A Randomized Convex-Concave Optimization Approach ⋮ On the Impossibility of Dimension Reduction for Doubling Subsets of $\ell_{p}$ ⋮ Large scale analysis of generalization error in learning using margin based classification methods ⋮ Similarity, kernels, and the fundamental constraints on cognition

Uses Software

• UCI-ml

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Database-friendly random projections: Johnson-Lindenstrauss with binary coins.
• Support-vector networks
• Large margin classification using the perceptron algorithm
• An algorithmic theory of learning: Robust concepts and random projection
• Extensions of Lipschitz mappings into a Hilbert space
• A PAC-Bayesian margin bound for linear classifiers
• Structural risk minimization over data-dependent hierarchies
• 10.1162/153244303321897681
• 10.1162/153244303765208403

This page was built for publication: Kernels as features: on kernels, margins, and low-dimensional mappings