Sciweavers

3995 search results - page 522 / 799
» Linearization of hybrid processes
Sort
View
CORR
2010
Springer
134views Education» more  CORR 2010»
15 years 5 months ago
The LASSO risk for gaussian matrices
We consider the problem of learning a coefficient vector x0 ∈ RN from noisy linear observation y = Ax0 + w ∈ Rn . In many contexts (ranging from model selection to image proce...
Mohsen Bayati, Andrea Montanari
JAIR
2010
115views more  JAIR 2010»
15 years 5 months ago
An Investigation into Mathematical Programming for Finite Horizon Decentralized POMDPs
Decentralized planning in uncertain environments is a complex task generally dealt with by using a decision-theoretic approach, mainly through the framework of Decentralized Parti...
Raghav Aras, Alain Dutech
JMLR
2010
135views more  JMLR 2010»
15 years 5 months ago
Bundle Methods for Regularized Risk Minimization
A wide variety of machine learning problems can be described as minimizing a regularized risk functional, with different algorithms using different notions of risk and differen...
Choon Hui Teo, S. V. N. Vishwanathan, Alex J. Smol...
TON
2010
118views more  TON 2010»
15 years 5 months ago
ILP formulations for p-cycle design without candidate cycle enumeration
—The concept of p-cycle (preconfigured protection cycle) allows fast and efficient span protection in wavelength division multiplexing (WDM) mesh networks. To design p-cycles f...
Bin Wu, Kwan L. Yeung, Pin-Han Ho
QEST
2010
IEEE
15 years 4 months ago
Reasoning about MDPs as Transformers of Probability Distributions
We consider Markov Decision Processes (MDPs) as transformers on probability distributions, where with respect to a scheduler that resolves nondeterminism, the MDP can be seen as ex...
Vijay Anand Korthikanti, Mahesh Viswanathan, Gul A...