In practical situations, the clustering result must be stable against points missing in the input data so that we can make trustworthy andconsistentdecisions.

Neural Information Processing Systems http://nips.cc/

Co-Training: We argue that our proposed training algorithm does indeed fit in the co-training framework.

Studying the behavior of non-human primates is essential for gaining evolutionary insights (Langer-graber et al., 2012), conducting biomedical research (Schapiro et al., 2005), and improving animal

Generalization for streaming and distributed (big) data is trivial.

FedAvg: FedAvg [29] has become a de facto standard federated learning algorithm in practice. However,it has several limitations as discussed in many papers, including [23]. It is also difficult to analyze convergence of FedAvg, especially in the nonconvex case andheterogeneity settings (both statistical andsystem heterogeneity). Moreover,FedAvg originally specifies SGD with a fixed number of epochs and a fixed learning rate as its local solver,making itlessflexible inpractice.