Tuning Metaheuristics: A Machine Learning PerspectiveThis book lays the foundations for a scientific approach to tuning metaheuristics. The fundamental intuition that underlies Birattari's approach is that the tuning problem has much in common with the problems that are typically faced in machine learning. |
Other editions - View all
Common terms and phrases
adopted algorithms under analysis ant colony optimization applications basis Birattari brute-force approach candidate configurations Chapter Cheat10 Chiarandini class of instances colony optimization combinatorial optimization combinatorial optimization problems computation concerns considered cost defined definition distribution Dorigo empirical risk estimate evaluation evolutionary computation example expected value experimental methodology experiments F-Race feature selection formal free lunch theorem Friedman test given hand heuristics implementation input iterated local search lazy learning learning machine machine learning Mario’s Metaheuristics Network method neural network number of candidates observed over-tuning parameters particular phase polynomial possible prediction prob probability measure problem of tuning procedure proposed QUADRATIC ASSIGNMENT racing algorithms racing approach sample Section simulated annealing solution solve specific statistical test stochastic Stützle subclass subset supervised learning tabu search test instances test set tion tNo-Race training set traveling salesman problem tuning algorithms tuning instances tuning metaheuristics tuning problem typically variables variance