MDL-based regularization, which balances data fit with a network's encoding length, preserves perfect solutions on several formal-language tasks, while standard L1, L2, and no regularization degrade them.
Minimum Description Length Hopfield Networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Associative memory architectures are designed for memorization but also offer, through their retrieval method, a form of generalization to unseen inputs: stored memories can be seen as prototypes from this point of view. Focusing on Modern Hopfield Networks (MHN), we show that a large memorization capacity undermines the generalization opportunity. We offer a solution to better optimize this tradeoff. It relies on Minimum Description Length (MDL) to determine during training which memories to store, as well as how many of them.
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
A Minimum Description Length Approach to Regularization in Neural Networks
MDL-based regularization, which balances data fit with a network's encoding length, preserves perfect solutions on several formal-language tasks, while standard L1, L2, and no regularization degrade them.