In this paper, we propose an efficient and effective training scheme coined as Sparse SAM (SSAM), which achieves sparse perturbation by a binary mask.

Recently, federated multi-view clustering (FedMVC) has emerged to explore cluster structures in multi-view data distributed on multiple clients. Many existing approaches tend to assume that clients are isomorphic and all of them belong to either single-view clients or multi-view clients.

However,sincetheinitial large learning rate generally helps the optimizer to converge to flatter minima, we hypothesize that the winning tickets have relatively sharp minima, which is considered a disadvantage in terms of generalization ability.

We report top-1 center-crop accuracy on the validation split of ImageNet,Places205andiNaturalist18.

Itfollows from (2) thatX Np(0, (eB,e )), where (eB,e ): = (I eB) Te (I eB) 1. (3) Wewillassumethat 0, andmoreoverthatrmin( ) rmax( ) 1, i.e. theeigenvaluesof are boundedawayfrom0and1. See (47) inthesupplement ( ;s), which conditionnumber ofsizeO(s).