Sciweavers

PAMI
2012
11 years 10 months ago
Sparse Algorithms Are Not Stable: A No-Free-Lunch Theorem
Abstract—We consider two desired properties of learning algorithms: sparsity and algorithmic stability. Both properties are believed to lead to good generalization ability. We sh...
Huan Xu, Constantine Caramanis, Shie Mannor
CORR
2012
Springer
198views Education» more  CORR 2012»
12 years 3 months ago
Lipschitz Parametrization of Probabilistic Graphical Models
We show that the log-likelihood of several probabilistic graphical models is Lipschitz continuous with respect to the ￿p-norm of the parameters. We discuss several implications ...
Jean Honorio
AAAI
2011
12 years 7 months ago
Improving Semi-Supervised Support Vector Machines Through Unlabeled Instances Selection
Semi-supervised support vector machines (S3VMs) are a kind of popular approaches which try to improve learning performance by exploiting unlabeled data. Though S3VMs have been fou...
Yu-Feng Li, Zhi-Hua Zhou
IJON
2011
158views more  IJON 2011»
13 years 2 months ago
Maximal Discrepancy for Support Vector Machines
Several theoretical methods have been developed in the past years to evaluate the generalization ability of a classifier: they provide extremely useful insights on the learning ph...
Davide Anguita, Alessandro Ghio, Sandro Ridella
ISNN
2010
Springer
13 years 6 months ago
Extension of the Generalization Complexity Measure to Real Valued Input Data Sets
Abstract. This paper studies the extension of the Generalization Complexity (GC) measure to real valued input problems. The GC measure, defined in Boolean space, was proposed as a...
Iván Gómez, Leonardo Franco, Jos&eac...
ICONIP
2008
13 years 9 months ago
A Notable Swarm Approach to Evolve Neural Network for Classification in Data Mining
This paper presents a novel and notable swarm approach to evolve an optimal set of weights and architecture of a neural network for classification in data mining. In a distributed ...
Satchidananda Dehuri, Bijan Bihari Misra, Sung-Bae...
IWANN
2005
Springer
14 years 29 days ago
Role of Function Complexity and Network Size in the Generalization Ability of Feedforward Networks
The generalization ability of different sizes architectures with one and two hidden layers trained with backpropagation combined with early stopping have been analyzed. The depend...
Leonardo Franco, José M. Jerez, José...
ICML
2008
IEEE
14 years 8 months ago
Query-level stability and generalization in learning to rank
This paper is concerned with the generalization ability of learning to rank algorithms for information retrieval (IR). We point out that the key for addressing the learning proble...
Yanyan Lan, Tie-Yan Liu, Tao Qin, Zhiming Ma, Hang...