79 search results - page 7 / 16 » Adaptive Online Gradient Descent |
118
click to vote
ICDCS
2007
IEEE
15 years 3 months ago
2007
IEEE
On-line decision making often involves query processing over time-varying data which arrives in the form of data streams from distributed locations. In such environments typically...
108
click to vote
TNN
2008
14 years 11 months ago
2008
This brief presents an efficient and scalable online learning algorithm for recurrent neural networks (RNNs). The approach is based on the real-time recurrent learning (RTRL) algor...
122
click to vote
JMLR
2008
14 years 11 months ago
2008
Log-linear and maximum-margin models are two commonly-used methods in supervised machine learning, and are frequently used in structured prediction problems. Efficient learning of...
NIPS
2007
15 years 1 months ago
2007
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...
107
click to vote
COLT
2006
Springer
15 years 3 months ago
2006
Springer
In an online convex optimization problem a decision-maker makes a sequence of decisions, i.e., chooses a sequence of points in Euclidean space, from a fixed feasible set. After ea...