Affine recurrent networks cannot correct errors along state-separating subspaces and thus learn only finite-horizon state tracking that predictably fails when within-class spread exceeds initial between-class separation.
The expressive limits of diagonal SSMs for state-tracking
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Rethinking State Tracking in Recurrent Models Through Error Control Dynamics
Affine recurrent networks cannot correct errors along state-separating subspaces and thus learn only finite-horizon state tracking that predictably fails when within-class spread exceeds initial between-class separation.