3049 search results - page 109 / 610 » On the Convergence of Bound Optimization Algorithms |
141
click to vote
FSTTCS
1995
Springer
15 years 8 months ago
1995
Springer
Karp and Zhang developed a general randomized parallel algorithm for solving branch and bound problems. They showed that with high probability their algorithm attained optimal spe...
137
click to vote
NIPS
2007
15 years 6 months ago
2007
We present a general boosting method extending functional gradient boosting to optimize complex loss functions that are encountered in many machine learning problems. Our approach...
159
Voted
COCOON
2006
Springer
15 years 8 months ago
2006
Springer
We study the dynamic bin packing problem introduced by Coffman, Garey and Johnson. This problem is a generalization of the bin packing problem in which items may arrive and depart...
235
Voted
ICAART
2010
INSTICC
16 years 1 months ago
2010
INSTICC
There has been a lot of recent work on Bayesian methods for reinforcement learning exhibiting near-optimal online performance. The main obstacle facing such methods is that in most...
128
click to vote
AAAI
2006
15 years 6 months ago
2006
Real-time dynamic programming (RTDP) is a heuristic search algorithm for solving MDPs. We present a modified algorithm called Focused RTDP with several improvements. While RTDP ma...