Sciweavers

7773 search results - page 416 / 1555
» On generalized Frame-Stewart numbers
Sort
View
JMLR
2012
13 years 9 months ago
Krylov Subspace Descent for Deep Learning
In this paper, we propose a second order optimization method to learn models where both the dimensionality of the parameter space and the number of training samples is high. In ou...
Oriol Vinyals, Daniel Povey
JMLR
2012
13 years 9 months ago
Algorithms for Learning Kernels Based on Centered Alignment
This paper presents new and effective algorithms for learning kernels. In particular, as shown by our empirical results, these algorithms consistently outperform the so-called uni...
Corinna Cortes, Mehryar Mohri, Afshin Rostamizadeh
INFOCOM
2012
IEEE
13 years 9 months ago
Jointly optimal bit loading, channel pairing and power allocation for multi-channel relaying
Abstract—We aim to enhance the end-to-end rate of a general dual-hop relay network with multiple channels and finite modulation formats, by jointly optimizing channel pairing, p...
Mahdi Hajiaghayi, Min Dong, Ben Liang
155
Voted
JCT
2008
76views more  JCT 2008»
15 years 6 months ago
Quadruple systems with independent neighborhoods
A 4-graph is odd if its vertex set can be partitioned into two sets so that every edge intersects both parts in an odd number of points. Let b(n) = max n 3 + (n - ) 3 = 1 2 + o...
Zoltán Füredi, Dhruv Mubayi, Oleg Pikh...
168
Voted
SSPR
1998
Springer
15 years 11 months ago
Regularization by Adding Redundant Features
The Pseudo Fisher Linear Discriminant (PFLD) based on a pseudo-inverse technique shows a peaking behaviour of the generalization error for training sample sizes that are about the...
Marina Skurichina, Robert P. W. Duin