arXiv Machine Learning By Simon Dr\"ager

Task-Restricted Symmetries in Recurrent Weight Space

Read the original on arXiv Machine Learning →

arXiv:2606. 18457v1 Announce Type: new Abstract: Recurrent networks can contain substantial functional redundancy in weight space: changing a recurrent matrix may leave the input-output rollout nearly unchanged on a task distribution, while similar-scale changes can destroy the same behavior.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning
23h ago

Dynamic Compression in Recurrent Networks

arXiv:2608. 17896v1 Announce Type: new Abstract: Recurrent models process long contexts efficiently by compressing their history into a fixed-size state, but modern architectures typically do so in a single causal pass over the sequence.

By Jyothish Pari, Ryan Bahlous-Boldi, Pulkit Agrawal
arXiv AI
Jun 9

MinMax Recurrent Neural Cascades

arXiv:2605. 06384v3 Announce Type: replace-cross Abstract: We introduce MinMax Recurrent Neural Cascades (MinMax RNCs), a class of recurrent neural networks built from a novel form of recurrence over the MinMax algebra.

By Alessandro Ronca