Unlike the conventional machine learning paradigms where learning is performed on a static dataset, domain incremental learning, i.e., continual learning with evolving domains, hopes to accommodate the model to the dynamically changing data distributions, while retaining the knowledge learned from previous domains [

We provide additional information about our network architecture. The backbone of our network is based on a standard PyTorch implementation of multi-scale grouping PointNet++. In our implementation, we set D = 128 . The detailed structure of the transformer module can be seen in Figure 1 . Regarding the primal-dual descriptor, we set its feature dimension to d = 256 .

Albeit, the objective of the learner is to achieve low task loss at an individual instance level.

Differential privacy (DP) has emerged as a rigorous notion to quantify data privacy. Subsequently, Rényi differential privacy (RDP) has become an alternative to the ordinary DP notion in both theoretical and empirical studies, because of its convenient compositional rules and flexibility. However, most mechanisms with DP (RDP) guarantees are essentially based on randomizing a fixed, finite-dimensional vector output. In this work, following Hall et al. [12] we further extend RDP to functional outputs, where the output space can be infinite-dimensional, and develop all necessary tools, e.g.