We describe an approach that uses combinatorial optimization and machine learning to share the work between the host and device of heterogeneous computing systems such that the overall application execution time is minimized. We propose to use combinatorial optimization to search for the optimal system configuration in the given parameter space (such as, the number of threads, thread affinity, work distribution for the host and device). For each system configuration that is suggested by combinatorial optimization, we use machine learning for evaluation of the system performance. We evaluate our approach experimentally using a heterogeneous platform that comprises two 12-core Intel Xeon E5 CPUs and an Intel Xeon Phi 7120P co-processor with 61 cores. Using our approach we are able to find a near-optimal system configuration by performing only about 5% of all possible experiments.