In this paper, we dive deeper into this class of strategies.

The method begins with an iterative Gaussian cloud soft clustering module, offering structured temporal point cloud representations.

Symmetries are prevalent in deep learning and can significantly influence the learning dynamics of neural networks. In this paper, we examine how exponential symmetries - a broad subclass of continuous symmetries present in the model architecture or loss function - interplay with stochastic gradient descent (SGD). We first prove that gradient noise creates a systematic motion (a "Noether flow") of the parameters θ along the degenerate direction to a unique initialization-independent fixed point θ

Contrastive learning has recently emerged as a promising approach for learning data representations that discover and disentangle the explanatory factors of the data.

One way to achieve this is through triangular mappings [Baptista et al., 2020, Spantini et al., 2022],