Sciweavers

101 search results - page 4 / 21
» Convergence of Gradient Dynamics with a Variable Learning Ra...
Sort
View
MP
2011
13 years 2 months ago
A first-order interior-point method for linearly constrained smooth optimization
Abstract: We propose a first-order interior-point method for linearly constrained smooth optimization that unifies and extends first-order affine-scaling method and replicator d...
Paul Tseng, Immanuel M. Bomze, Werner Schachinger
ICML
2007
IEEE
14 years 8 months ago
Exponentiated gradient algorithms for log-linear structured prediction
Conditional log-linear models are a commonly used method for structured prediction. Efficient learning of parameters in these models is therefore an important problem. This paper ...
Amir Globerson, Terry Koo, Xavier Carreras, Michae...
IJCAI
2001
13 years 9 months ago
Exploiting Multiple Secondary Reinforcers in Policy Gradient Reinforcement Learning
Most formulations of Reinforcement Learning depend on a single reinforcement reward value to guide the search for the optimal policy solution. If observation of this reward is rar...
Gregory Z. Grudic, Lyle H. Ungar
ICML
2003
IEEE
14 years 8 months ago
Optimization with EM and Expectation-Conjugate-Gradient
We show a close relationship between the Expectation - Maximization (EM) algorithm and direct optimization algorithms such as gradientbased methods for parameter learning. We iden...
Ruslan Salakhutdinov, Sam T. Roweis, Zoubin Ghahra...
JMLR
2010
105views more  JMLR 2010»
13 years 2 months ago
On the Convergence Properties of Contrastive Divergence
Contrastive Divergence (CD) is a popular method for estimating the parameters of Markov Random Fields (MRFs) by rapidly approximating an intractable term in the gradient of the lo...
Ilya Sutskever, Tijmen Tieleman