A Communication Complexity Lower Bound for Nonuniformly Convex Consensus Optimization

Abstract

We study the communication complexity of convex decentralized optimization over time-varying networks, where $n$ nodes hold private functions and must agree on the global minimizer using only synchronous exchanges with neighbors. The cost is the number of communication rounds to reach accuracy $\varepsilon$ -- a measure akin to round complexity in the LOCAL model, but constrained by nodes sharing only oracle responses. We prove a new lower bound of $\Omega\!\left(\chi_{\mathcal G} \sqrt{\kappa_g}\,\log\frac{n}{\chi_{\mathcal G}}\log\frac1\varepsilon\right)$ communication rounds, where $\chi_{\mathcal G}$ is the condition number of the network Laplacians and $\kappa_g$ that of the global objective, showing the round complexity attainable under uniform regularity cannot be matched in the nonuniform regime. The construction rests on spectral graph theory: we embed time-rotating star gadgets into the edges of an expander and patch them to preserve spectral connectivity.