Quoted By:
I order to make a game you must consider minimizing a sum of local convex objective functions in a distributed setting, where communication can be costly and propose and analyze a class of nested distributed gradient methods with adaptive quantized communication (NEAR-DGD+Q) and show the effect of performing multiple quantized communication steps on the rate of convergence and on the size of the neighborhood of convergence, and prove R-Linear convergence to the exact solution with increasing number of consensus steps and adaptive quantization and be able to test the performance of the method, as well as some practical variants, on quadratic functions, and show the effects of multiple quantized communication steps in terms of iterations/gradient evaluations, communication and cost.
