Preconditioned delta-rule models with a diagonal curvature approximation improve upon standard DeltaNet, GDN, and KDA by better approximating the test-time regression objective.
K., Hutter, F., and Pontil, M
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Linear recurrent filters exactly reproduce HMM belief logits under deterministic transitions and achieve near-zero decoding error under nearly deterministic ones, extending to action-controlled cases.
citing papers explorer
-
Preconditioned DeltaNet: Curvature-aware Sequence Modeling for Linear Recurrences
Preconditioned delta-rule models with a diagonal curvature approximation improve upon standard DeltaNet, GDN, and KDA by better approximating the test-time regression objective.
-
Why Linear Recurrent Memory Works in Partially Observable Reinforcement Learning
Linear recurrent filters exactly reproduce HMM belief logits under deterministic transitions and achieve near-zero decoding error under nearly deterministic ones, extending to action-controlled cases.