Federated learning (FL) is a machine learning paradigm where multiple client devices train models collaboratively without data exchange.

Manypublished baselines are hard to compare to one another due to varying degrees of HP tuning.

This presents aproblem for certifying unseen points asthe ground truth cannot be known. We therefore stipulate that certification must be independent of the true label of the point being certified. Moreover, replacing the ground truth with the predicted label is unsatisfactory,because thepurpose ofgeneralizing totop-k predictions istoconsider cases where anyofthepredictionsinFk(x)maybecorrect. Wewouldthusliketopredict only whenm(S,x) < 0. To accomplish this we create an instrumented model,g, as given by EquationB2. First, by applying (C7), we obtain (C8).

Certifiablelocalrobustness,which rigorouslyprecludes small-normadversarial examples, has received significant attention as a means of addressing security concerns in deep learning.

When deploying machine learning estimators in science and engineering (SAE) domains, it is critical to avoid failed estimations that can have disastrous consequences, e.g., in aero engine design.

Sampling from a complex distributionπ and approximating its intractable normalizing constantZ are challenging problems.