Towfic, Zaid J.Chen, JianshuSayed, Ali H.2017-12-192017-12-192017-12-19201310.1016/j.neucom.2012.12.043https://infoscience.epfl.ch/handle/20.500.14299/143313In this work, we analyze the generalization ability of distributed online learning algorithms under stationary and non-stationary environments. We derive bounds for the excess-risk attained by each node in a connected network of learners and study the performance advantage that diffusion has over individual non-cooperative processing. We conduct extensive simulations to illustrate the results.text::journal::journal article::research article