NeurIPS 2020

Proximal Mapping for Deep Regularization

Meta Review

This paper discusses using proximal mappings as a regularization technique. It concretely proposes and experimentally evaluates two such regularizers: One that encourages an LSTM to be robust to changes in its inputs, and one that regularizes embeddings to be close to each other in multi-view learning. The reviewers all agreed that the method was clearly presented, well-motivated, and an important contribution. The consensus is therefore to accept.