arXiv (All)
open access
High-probability guarantees for linear accessibility in feature superposition
Neural networks can leverage feature superposition to encode more concepts than dimensions, but cross-feature interference constrains the linear accessibility of simultaneously active features. By framing linear accessibility as a compressed sensing problem, we derive high-probability bounds for fix
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Robust LassoNet: Enhancing Feature Selection in Neural Networks via Robust Loss Functions#1142864
- Towards a mathematical theory of superposition#780850
- Towards a mathematical theory of superposition#779475
- Signal-Noise Factorization Isolates Nuisance Variation into Removable Subspaces#1155686
- Beyond the universal law of robustness: Sharper laws for random features and neural tangent kernels#1158453
Record · ID 987294
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive