Stochastic gradients closely relate to both optimization and generalization of deep neural networks (DNNs).

Multi-modal contrastive representation (MCR) of more than three modalities is critical in multi-modal learning.

To tackle this problem, we rigorously analyze a representative distillation-based algorithm in the view of kernel regression.

These results are then generalized to general models and likelihoods, where the same claims hold.

However, an emerging issue in allocation problems is data privacy.