Distributed spectrum sharing algorithms enabled by the spectrum control plane represent one of the fundamental research thrusts being considered for the SII center. Results from earlier work show that simple local heuristics for interference avoidance can provide significant performance gains relative to uncoordinated operation, while offering lower transaction costs when compared with more centralized optimization strategies. In market environments where full coordination across heterogeneous networks may not be achievable (e.g., because strategic conflicts may arise when LTE cellular operators share with unaffiliated WiFi networks), autonomous sharing strategies may be especially valuable and may complement more centralized optimization. Accordingly, a key research objective for the SII program is evaluation of cross-layer autonomous/distributed sharing algorithms in fundamental terms and then assess their prospective viability for real-world use cases. We plan to consider hybrid centralized/distributed algorithms where edge cloud services may be used to achieve enhanced performance via improved regional awareness of spectrum use. This thrust area also includes the study of machine learning enhancements to spectrum sharing algorithms which can further improve system performance, particularly in decentralized scenarios.