This algorithm progressively decreases the length scale, expanding the class of functions considered by the optimizer.

Modern deep learning is driven by first-order stochastic optimization algorithms.

Modern deep learning is driven by first-order stochastic optimization algorithms.

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"

We show that the answer to this question depends on the properties of underlying preference distributions.