Hong Wang

Exact Decentralized Optimization via Explicit $\ell_1$ Consensus Penalties

Categories Network Optimization, Nonlinear Optimization Tags ,

Consensus optimization enables autonomous agents to solve joint tasks through peer-to-peer exchanges alone. Classical decentralized gradient descent is appealing for its minimal state but fails to achieve exact consensus with fixed stepsizes unless additional trackers or dual variables are introduced. We revisit penalty methods and introduce a decentralized two-layer framework that couples an outer penalty-continuation … Read more

Local Acceptance without Global Agreement: Convergence of Decentralized Trust-Region Methods

Categories Parallel Algorithms Tags , ,

We study decentralized smooth nonconvex optimization with a lower-bounded average objective and independent local trust-region acceptance decisions. Successful local trials can increase the average objective, while rejection produces a zero accepted inverse block at a nonzero gradient tracker. Our main contribution is a convergence analysis that permits such genuine local rejections. The method combines gradient … Read more