Table 3 The results on optimization of ground state energy of SK model compared to extremal optimization (EO), genetic algorithm (GA), and simulated annealing (SA)
From: Gumbel-softmax-based optimization: a simple general framework for optimization problems on graphs
N | I | EO [28] | GAa | SA | GSO (\(N_{{\text{bs}}}=1\))b |
|---|---|---|---|---|---|
256 | 5000 | \(-\,\)0.74585(2)/\(\sim\)268 s | \(-\,\)0.6800(3)/16.3 s | \(-\,\)0.7278(2)/1.28 s | \(-\,\)0.7267(2)/0.99 s |
512 | 2500 | \(-\,\)0.75235(3)/\(\sim\)1.2 h | \(-\,\)0.6580(3)/60.06 s | \(-\,\)0.7327(2)/3.20 s | \(-\,\)0.7405(2)/2.16 s |
1024 | 1250 | 0.7563(2)/\(\sim\)20 h | \(-\,\)0.6884(4)/236.21 s | \(-\,\)0.7352(2)/15.27 s | \(-\,\)0.7480(2)/4.49 s |
2048 | 400 | – | – | \(-\,\)0.7367(2)/63.27 s | \(-\,\)0.7524(2)/7.23 s |
4096 | 200 | – | – | \(-\,\)0.73713(6)/1591.93 s | \(-\,\)0.7551(2)/10.46 s |
8192 | 100 | – | – | – | \(-\,\)0.7562(1)/25.15 s |