Over-determined linear system of equations -> solvable. m2sat_to_bip.py in contrib.Įasy, create equation system from the upper triangular part of the matrix (triu).
Very complex to learn, but possible? C.f. Reversing some problems like Quadratic Knapsack might be possible - an algorithm is an idea, but one could also make their life easy and try fitting a NN model to it. Thus we can recreate the graph and other input parameters given a GraphColoring QUBO matrix. This shows whether we can deduce the parameters that led to a QUBO matrix, given we predicted the problem beforehand.Ī lot of the graph based problems are easily reversable since the graph structure is kept intact in the QUBO matrix. Each line represents 10 models and includes the 95% confidence interval.
Some of the problems are easily learned by a neural network regressor. The t-SNE plot for this experiment is shown below. Size, which most of the time is 64圆4 and in rare cases goes up to 144x144 (for The smaller sizes are zero-padded to the biggest supported the datasetĬonsists of not just 64圆4 QUBO matrices for each problem, but also smaller Note that this is using a generalized dataset, i.e. Total misclassification rate over 20 models goes to near zero. Using parameter configuration 100_genX (see simulations.json), the average Given some QUBO matrix that was generated using a set of problem parameters, we first classify the problem in step a and then predict the parameters in step b. > from qubo_nn.problems import PROBLEM_REGISTRY Contains plotting scripts and generated plots.Ĭontains generators and evaluators for specific problems such as 3SAT or TSP.Įnd to end training and testing of NNs on QUBO matrices.
0 kommentar(er)
