Florida International University
Edit Your Profile
FIU Discovery
Toggle navigation
Browse
Home
People
Organizations
Scholarly & Creative Works
Research Facilities
Support
Edit Your Profile
Generalization and robustness of batched weighted average algorithm with V-geometrically ergodic Markov data
Conference
Cuong, NV, Ho, LST, Dinh, V. (2013). Generalization and robustness of batched weighted average algorithm with V-geometrically ergodic Markov data .
EURO-PAR 2011 PARALLEL PROCESSING, PT 1,
8139 LNAI 264-278. 10.1007/978-3-642-40935-6_19
Share this citation
Twitter
Email
Cuong, NV, Ho, LST, Dinh, V. (2013). Generalization and robustness of batched weighted average algorithm with V-geometrically ergodic Markov data .
EURO-PAR 2011 PARALLEL PROCESSING, PT 1,
8139 LNAI 264-278. 10.1007/978-3-642-40935-6_19
Copy Citation
Share
Overview
Identifiers
Additional Document Info
View All
Overview
cited authors
Cuong, NV; Ho, LST; Dinh, V
authors
Nguyen, Viet Cuong
abstract
We analyze the generalization and robustness of the batched weighted average algorithm for V-geometrically ergodic Markov data. This algorithm is a good alternative to the empirical risk minimization algorithm when the latter suffers from overfitting or when optimizing the empirical risk is hard. For the generalization of the algorithm, we prove a PAC-style bound on the training sample size for the expected L1-loss to converge to the optimal loss when training data are V-geometrically ergodic Markov chains. For the robustness, we show that if the training target variable's values contain bounded noise, then the generalization bound of the algorithm deviates at most by the range of the noise. Our results can be applied to the regression problem, the classification problem, and the case where there exists an unknown deterministic target hypothesis. © 2013 Springer-Verlag.
publication date
November 18, 2013
published in
DISTRIBUTED COMPUTING (DISC 2014)
Book
Identifiers
Digital Object Identifier (DOI)
https://doi.org/10.1007/978-3-642-40935-6_19
Additional Document Info
start page
264
end page
278
volume
8139 LNAI