Efficient Global Optimization of Expensive Black-Box Functions
Journal of Global Optimization
The Journal of Machine Learning Research
Continuous Lunches Are Free Plus the Design of Optimal Optimization Algorithms
Algorithmica - Including a Special Section on Genetic and Evolutionary Computation; Guest Editors: Benjamin Doerr, Frank Neumann and Ingo Wegener
General lower bounds for evolutionary algorithms
PPSN'06 Proceedings of the 9th international conference on Parallel Problem Solving from Nature
Ordinal regression in evolutionary computation
PPSN'06 Proceedings of the 9th international conference on Parallel Problem Solving from Nature
Bandit based monte-carlo planning
ECML'06 Proceedings of the 17th European conference on Machine Learning
Consistency modifications for automatically tuned Monte-Carlo tree search
LION'10 Proceedings of the 4th international conference on Learning and intelligent optimization
Continuous upper confidence trees
LION'05 Proceedings of the 5th international conference on Learning and Intelligent Optimization
Upper confidence tree-based consistent reactive planning application to minesweeper
LION'12 Proceedings of the 6th international conference on Learning and Intelligent Optimization
Hi-index | 0.00 |
Following a number of recent papers investigating the possibility of optimal comparison-based optimization algorithms for a given distribution of probability on fitness functions, we (i) discuss the comparison-based constraints (ii) choose a setting in which theoretical tight bounds are known (iii) develop a careful implementation using billiard algorithms, Upper Confidence trees and (iv) experimentally test the tractability of the approach. The results, on still very simple cases, show that the approach, yet still preliminary, could be tested successfully until dimension 10 and horizon 50 iterations within a few hours on a standard computer, with convergence rate far better than the best algorithms.