Sciweavers

Share
JSCIC
2010
97views more  JSCIC 2010»
8 years 7 days ago
Finite Element Characteristic Methods Requiring no Quadrature
The characteristic methods are known to be very efficient for convection-diffusion problems including the Navier-Stokes equations. Convergence is established when the integrals ar...
Olivier Pironneau
JMLR
2010
189views more  JMLR 2010»
8 years 7 days ago
Adaptive Step-size Policy Gradients with Average Reward Metric
In this paper, we propose a novel adaptive step-size approach for policy gradient reinforcement learning. A new metric is defined for policy gradients that measures the effect of ...
Takamitsu Matsubara, Tetsuro Morimura, Jun Morimot...
ACL
2009
8 years 3 months ago
Stochastic Gradient Descent Training for L1-regularized Log-linear Models with Cumulative Penalty
Stochastic gradient descent (SGD) uses approximate gradients estimated from subsets of the training data and updates the parameters in an online fashion. This learning framework i...
Yoshimasa Tsuruoka, Jun-ichi Tsujii, Sophia Anania...
SIGMETRICS
2010
ACM
155views Hardware» more  SIGMETRICS 2010»
8 years 3 months ago
Blackbox prediction of the impact of DVFS on end-to-end performance of multitier systems
Dynamic voltage and frequency scaling (DVFS) is a wellknown technique for gaining energy savings on desktop and laptop computers. However, its use in server settings requires care...
Shuyi Chen, Kaustubh R. Joshi, Matti A. Hiltunen, ...
NN
2010
Springer
125views Neural Networks» more  NN 2010»
8 years 3 months ago
Parameter-exploring policy gradients
We present a model-free reinforcement learning method for partially observable Markov decision problems. Our method estimates a likelihood gradient by sampling directly in paramet...
Frank Sehnke, Christian Osendorfer, Thomas Rü...
SIMPRA
2008
99views more  SIMPRA 2008»
8 years 5 months ago
Response surface methodology for constrained simulation optimization: An overview
This article summarizes `Generalized Response Surface Methodology'(GRSM), extending Box and Wilson's `Response Surface Methodology'(RSM). GRSM allows multiple rando...
Jack P. C. Kleijnen
CGF
2008
132views more  CGF 2008»
8 years 5 months ago
Irradiance Gradients in the Presence of Participating Media and Occlusions
In this paper we present a technique for computing translational gradients of indirect surface reflectance in scenes containing participating media and significant occlusions. The...
Wojciech Jarosz, Matthias Zwicker, Henrik Wann Jen...
NIPS
1997
8 years 6 months ago
Gradients for Retinotectal Mapping
The initial activity-independent formation of a topographic map in the retinotectal system has long been thought to rely on the matching of molecular cues expressed in gradients i...
Geoffrey J. Goodhill
DAWAK
2007
Springer
8 years 11 months ago
Mining Top-K Multidimensional Gradients
Several business applications such as marketing basket analysis, clickstream analysis, fraud detection and churning migration analysis demand gradient data analysis. By employing g...
Ronnie Alves, Orlando Belo, Joel Ribeiro
ICIP
2008
IEEE
8 years 12 months ago
Stochastic fusion of multi-view gradient fields
Image gradients form powerful cues in a host of vision and graphics applications. In this paper, we consider multiple views of a textured planar scene and consider the problem of ...
Aswin C. Sankaranarayanan, Rama Chellappa
books