Task-Restricted Symmetries in Recurrent Weight Space

June 16, 2026 ยท Grace Period ยท ๐Ÿ› the ICML 2026 Workshop on Weight-Space Symmetries

โณ Grace Period
This paper is less than 90 days old. We give authors time to release their code before passing judgment.
Authors Simon Drรคger arXiv ID 2606.18457 Category cs.LG: Machine Learning Citations 0 Venue the ICML 2026 Workshop on Weight-Space Symmetries
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. We study this redundancy in one-layer tanh RNNs using ordered real Schur coordinates. The Schur form separates spectral blocks from directed nonnormal couplings, giving a diagnostic basis for structured ablations that keep the input and readout maps fixed. In a fixed-length copy task, selected nonnormal Schur couplings can be removed with little loss in some trained solutions, whereas other couplings are necessary for accurate autonomous replay. Across flip-flop, sine generation, and context-dependent integration, the loss-preserving ablation profile varies across tasks and trained solutions. These results identify candidate approximate functional invariances, not universal symmetries of recurrent weight space. Schur-coordinate ablations provide a practical diagnostic for which structured perturbations preserve a trained recurrent solution and which ones disrupt its computation.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Machine Learning