An Analysis of Attention via the Lens of Exchangeability and Latent Variable Models

arXiv:2212.14852v3 Announce Type: replace
Abstract: With the attention mechanism, transformers achieve significant empirical successes. Despite the intuitive understanding that transformers perform relational inference over long sequences to produce desirable representations, we lack a rigorous theory on how the attention mechanism achieves it. In particular, several intriguing questions remain open: (a) What makes a desirable representation? (b) How does the attention mechanism infer the desirable representation within the forward pass? (c) How does a pretraining procedure learn to infer the desirable …

abstract analysis arxiv attention cs.lg inference questions relational theory transformers type understanding via