Geometric deep learning enables the encoding of physical symmetries in modeling 3D objects.

The goal is to train a good instance classifier.

We show that GWG exhibits strong convergence guarantees.

By analyzing the loss landscape of a single Transformer layer using Softmax and Gaussian attention kernels, our work provides concrete answers to these questions.

We further provide numerical simulations to corroborate our theoretical findings.

However, these methods typically rely on strict assumptions and are limited to certain types of label noise. In this paper, we reformulate the label-noise problem from a generative-model perspective, i.e., labels are generated by gradually refining an initial random guess.