Global Convergence and Asymptotic Optimality of the Heavy Ball Method for a Class of Nonconvex Optimization Problems
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Control Systems Letters"
DOI: 10.1109/lcsys.2022.3163408
Abstract: In this letter we revisit the famous heavy ball method and study its global convergence for a class of non-convex problems with sector-bounded gradient. We characterize the parameters that render the method globally convergent and… read more here.
Keywords: heavy ball; global convergence; class; convergence ... See more keywords
Communication-Efficient Federated Learning Using Censored Heavy Ball Descent
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Transactions on Signal and Information Processing over Networks"
DOI: 10.1109/tsipn.2022.3212315
Abstract: Distributed machine learning enables scalability and computational offloading, but requires significant levels of communication. Consequently, communication efficiency in distributed learning settings is an important consideration, especially when the communications are wireless and battery-driven devices are… read more here.
Keywords: communication efficient; heavy ball; communication; chb ... See more keywords