However,untrusted data sources leavethe services vulnerable to poisoning attacks [5, 28], where adversaries can inject malicious training data to degrade model accuracy.

St Rs, sincetheproductmanifoldSt Rs is g-connected.

Inthiswork, we focus on a classification problem and investigate the behavior of both noncalibrated and calibrated negativelog-likelihood (CNLL) ofadeep ensemble as a function of the ensemble size and the member network size.

However, since this proof relies on the existence of a convergent subsequence, their proof does not reveal any rate forglobal convergence.