Generalization Bounds

2017 ◽  
pp. 556-556
Author(s):  
Mark Reid
Keyword(s):  
Generalization Bounds

scholarly journals Coarse-refinement dilemma: on generalization bounds for data clustering

2021 ◽  
pp. 115399
Author(s):  
Yule Vaz ◽  
Rodrigo Fernandes de Mello ◽  
Carlos Henrique Grossi Ferreira
Keyword(s):  
Data Clustering ◽  
Generalization Bounds

scholarly journals Consistency and Generalization Bounds for Maximum Entropy Density Estimation

Entropy ◽  
2013 ◽  
Vol 15 (12) ◽  
pp. 5439-5463 ◽  
Author(s):  
Shaojun Wang ◽  
Russell Greiner ◽  
Shaomin Wang
Keyword(s):  
Maximum Entropy ◽  
Density Estimation ◽  
Entropy Density ◽  
Generalization Bounds

Generalization Bounds with Integral Probability Metrics

2019 ◽  
pp. 75-92
Author(s):  
Ievgen Redko ◽  
Amaury Habrard ◽  
Emilie Morvant ◽  
Marc Sebban ◽  
Younès Bennani
Keyword(s):  
Probability Metrics ◽  
Generalization Bounds ◽  
Integral Probability

Generalization bounds of ERM algorithm with V-geometrically Ergodic Markov chains

2011 ◽  
Vol 36 (1) ◽  
pp. 99-114 ◽  
Author(s):  
Bin Zou ◽  
Zongben Xu ◽  
Xiangyu Chang
Keyword(s):  
Markov Chains ◽  
Generalization Bounds

ITERATIVE SELF-LABELING DOMAIN ADAPTATION FOR LINEAR STRUCTURED IMAGE CLASSIFICATION

2013 ◽  
Vol 22 (05) ◽  
pp. 1360005 ◽  
Author(s):  
AMAURY HABRARD ◽  
JEAN-PHILIPPE PEYRACHE ◽  
MARC SEBBAN
Keyword(s):  
Image Classification ◽  
Domain Adaptation ◽  
Research Area ◽  
Target Domain ◽  
Sparse Models ◽  
Similarity Functions ◽  
Generalization Bounds ◽  
Source Data ◽  
New Research ◽  
Target Data

A strong assumption to derive generalization guarantees in the standard PAC framework is that training (or source) data and test (or target) data are drawn according to the same distribution. Because of the presence of possibly outdated data in the training set, or the use of biased collections, this assumption is often violated in real-world applications leading to different source and target distributions. To go around this problem, a new research area known as Domain Adaptation (DA) has recently been introduced giving rise to many adaptation algorithms and theoretical results in the form of generalization bounds. This paper deals with self-labeling DA whose goal is to iteratively incorporate semi-labeled target data in the learning set to progressively adapt the classifier from the source to the target domain. The contribution of this work is three-fold: First, we provide the minimum and necessary theoretical conditions for a self-labeling DA algorithm to perform an actual domain adaptation. Second, following these theoretical recommendations, we design a new iterative DA algorithm, called GESIDA, able to deal with structured data. This algorithm makes use of the new theory of learning with (ε,γ,τ)-good similarity functions introduced by Balcan et al., which does not require the use of a valid kernel to learn well and allows us to induce sparse models. Finally, we apply our algorithm on a structured image classification task and show that self-labeling domain adaptation is a new original way to deal with scaling and rotation problems.

scholarly journals Sparse multinomial logistic regression: fast algorithms and generalization bounds

2005 ◽  
Vol 27 (6) ◽  
pp. 957-968 ◽  
Author(s):  
B. Krishnapuram ◽  
L. Carin ◽  
M.A.T. Figueiredo ◽  
A.J. Hartemink
Keyword(s):  
Logistic Regression ◽  
Multinomial Logistic Regression ◽  
Fast Algorithms ◽  
Generalization Bounds

Model complexity control for regression using VC generalization bounds

1999 ◽  
Vol 10 (5) ◽  
pp. 1075-1089 ◽  
Author(s):  
V. Cherkassky ◽  
Xuhui Shao ◽  
F.M. Mulier ◽  
V.N. Vapnik
Keyword(s):  
Model Complexity ◽  
Generalization Bounds ◽  
Complexity Control
Sign in / Sign up

Export Citation Format

Share Document