We consider learning in decentralized heterogeneous networks: agents seek to minimize a convex functional that aggregates data across the network, while only having access their local streams. focus on case where estimate regression function belongs reproducing kernel Hilbert space (RKHS). To incentivize coordination respecting network heterogeneity, we impose nonlinear proximity constraints. T...

We study a model of opinion exchange in social networks where state the world is realized and every agent receives zero-mean noisy signal state. It known from Golub Jackson that under DeGroot dynamics agents reach consensus which close to when network large. The dynamics, however, highly non-robust presence single `bot' does not adhere updating rule, can sway public any other value.