A guided Monte Carlo method for optimization problems

We introduce a new Monte Carlo method by incorporating a guided distribution function to the conventional Monte Carlo method. In this way, the efficiency of Monte Carlo methods is drastically improved. To further speed up the algorithm, we include two more ingredients into the algorithm. First, we freeze the sub-patterns that have high probability of appearance during the search for optimal solution, resulting in a reduction of the phase space of the problem. Second, we perform the simulation at a temperature which is within the optimal temperature range of the optimization search in our algorithm. We use this algorithm to search for the optimal path of the traveling salesman problem and the ground state energy of the spin glass model and demonstrate that its performance is comparable with more elaborate and heuristic methods.