Sciweavers

472 search results - page 62 / 95
» Linear programming with online learning
Sort
View
COLT
1998
Springer
13 years 12 months ago
Large Margin Classification Using the Perceptron Algorithm
We introduce and analyze a new algorithm for linear classification which combines Rosenblatt's perceptron algorithm with Helmbold and Warmuth's leave-one-out method. Like...
Yoav Freund, Robert E. Schapire
NIPS
1996
13 years 9 months ago
Multidimensional Triangulation and Interpolation for Reinforcement Learning
Dynamic Programming, Q-learning and other discrete Markov Decision Process solvers can be applied to continuous d-dimensional state-spaces by quantizing the state space into an arr...
Scott Davies
HT
2000
ACM
13 years 12 months ago
Reusable hypertext structures for distance and JIT learning
Software components for distance and just-in-time (JIT) learning are an increasingly common method of encouraging reuse and facilitating the development process[58], but no analog...
Anne Morgan Spalter, Rosemary Michelle Simpson
ICML
2008
IEEE
14 years 8 months ago
No-regret learning in convex games
Quite a bit is known about minimizing different kinds of regret in experts problems, and how these regret types relate to types of equilibria in the multiagent setting of repeated...
Geoffrey J. Gordon, Amy R. Greenwald, Casey Marks
AAAI
2011
12 years 7 months ago
Fast Newton-CG Method for Batch Learning of Conditional Random Fields
We propose a fast batch learning method for linearchain Conditional Random Fields (CRFs) based on Newton-CG methods. Newton-CG methods are a variant of Newton method for high-dime...
Yuta Tsuboi, Yuya Unno, Hisashi Kashima, Naoaki Ok...