Additive versus exponentiated gradient updates for linear prediction
STOC '95 Proceedings of the twenty-seventh annual ACM symposium on Theory of computing
Large Margin Classification Using the Perceptron Algorithm
Machine Learning - The Eleventh Annual Conference on computational Learning Theory
Learning Additive Models Online with Fast Evaluating Kernels
COLT '01/EuroCOLT '01 Proceedings of the 14th Annual Conference on Computational Learning Theory and and 5th European Conference on Computational Learning Theory
Learning from Labeled and Unlabeled Data using Graph Mincuts
ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
The Journal of Machine Learning Research
The Robustness of the p-Norm Algorithms
Machine Learning
A Second-Order Perceptron Algorithm
SIAM Journal on Computing
ICML '05 Proceedings of the 22nd international conference on Machine learning
Online Passive-Aggressive Algorithms
The Journal of Machine Learning Research
Manifold Regularization: A Geometric Framework for Learning from Labeled and Unlabeled Examples
The Journal of Machine Learning Research
On the Effectiveness of Laplacian Normalization for Graph Semi-supervised Learning
The Journal of Machine Learning Research
Predicting the labels of an unknown graph via adaptive exploration
Theoretical Computer Science
RolX: structural role extraction & mining in large graphs
Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining
Random spanning trees and the prediction ofweighted graphs
The Journal of Machine Learning Research
Hi-index | 0.00 |
The nearest neighborand the perceptronalgorithms are intuitively motivated by the aims to exploit the "cluster" and "linear separation" structure of the data to be classified, respectively. We develop a new online perceptron-like algorithm, Pounce, to exploit both types of structure. We refine the usual margin-based analysis of a perceptron-like algorithm to now additionally reflect the cluster-structure of the input space. We apply our methods to study the problem of predicting the labeling of a graph. We find that when both the quantity and extent of the clusters are small we may improve arbitrarily over a purely margin-based analysis.