Sciweavers

66 search results - page 6 / 14
» Stochastic gradient descent on GPUs
Sort
View
IVC
2007
142views more  IVC 2007»
13 years 9 months ago
Fast stochastic optimization for articulated structure tracking
Recently, an optimization approach for fast visual tracking of articulated structures based on Stochastic Meta-Descent (SMD) [7] has been presented. SMD is a gradient descent with...
Matthieu Bray, Esther Koller-Meier, Nicol N. Schra...
ISCAS
2006
IEEE
118views Hardware» more  ISCAS 2006»
14 years 3 months ago
A robust continuous-time multi-dithering technique for laser communications using adaptive optics
A robust system architecture to achieve optical coherency free optimization. Several methods that had been proposed in the in multiple-beam free-space laser communication links wit...
Dimitrios N. Loizos, Paul-Peter Sotiriadis, Gert C...
ATAL
2008
Springer
13 years 11 months ago
Stochastic search methods for nash equilibrium approximation in simulation-based games
We define the class of games called simulation-based games, in which the payoffs are available as an output of an oracle (simulator), rather than specified analytically or using a...
Yevgeniy Vorobeychik, Michael P. Wellman
ICML
2007
IEEE
14 years 10 months ago
Pegasos: Primal Estimated sub-GrAdient SOlver for SVM
We describe and analyze a simple and effective iterative algorithm for solving the optimization problem cast by Support Vector Machines (SVM). Our method alternates between stocha...
Shai Shalev-Shwartz, Yoram Singer, Nathan Srebro
NIPS
2007
13 years 11 months ago
Incremental Natural Actor-Critic Algorithms
We present four new reinforcement learning algorithms based on actor-critic and natural-gradient ideas, and provide their convergence proofs. Actor-critic reinforcement learning m...
Shalabh Bhatnagar, Richard S. Sutton, Mohammad Gha...