This paper investigates ML systems serving a group of users, with multiple models/services, each aimed at specializing to a sub-group of users.

In contrast, in non-private settings, practitioners commonly utilize "adaptive" hyperparameter optimization methods such as Gaussian process-based optimization, which select the next candidate based on information gathered from previous outputs. This substantial contrast between private and non-private hyperparameter optimization underscores a critical concern. In our paper, we introduce DP-HyPO, a pioneering framework for "adaptive"

Then we follow recent works to pursue the weak approximate solutions.

We formalize coherence --a requirement that erroneous predictions, within a slice, should be wrong for the same reason --as a key property that any slice discovery method should satisfy.