Convergence to a simplex ETF: Class means tend towards equinorm and equiangular vectors when centred about the global average.

Figure 1: Our approach--LoCo--offers memory-efficient learning of location-consistent (LoCo) features.

The word embedding space in neural models is skewed, and correcting this can improve task performance.

Training large neural networks requires substantial hardware and energy resources.

Evaluating machine learning models requires evaluation data.

A wide array of sequence models are built on a framework modeled after Transformers, comprising alternating sequence mixer and channel mixer layers.

Second, we show the first core-set w.r.t. the sum-of-nearest-neighbor distances. Finally, we run several experiments showing the effectiveness of our core-set approach. In particular, we apply constrained diversity maximization to summarize a set of timed messages that takes into account the messages' recency.