Develops algebraic geometry tools for monomial neural networks and proves the singular locus of neurovarieties is contained in the architectural degeneracy locus for fully connected networks with non-increasing widths and scalar output under layerwise regularity assumptions.
arXiv preprint arXiv:2401.16613 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
HORST uses non-commutative operator composition and a hyperbolic mirror map to combine stability from adaptive optimizers with L1 sparsity bias, outperforming AdamW across sparsity levels on vision and language tasks.
citing papers explorer
-
Algebraic Networks and Architectural Degenerations
Develops algebraic geometry tools for monomial neural networks and proves the singular locus of neurovarieties is contained in the architectural degeneracy locus for fully connected networks with non-increasing widths and scalar output under layerwise regularity assumptions.
-
HORST: Composing Optimizer Geometries for Sparse Transformer Training
HORST uses non-commutative operator composition and a hyperbolic mirror map to combine stability from adaptive optimizers with L1 sparsity bias, outperforming AdamW across sparsity levels on vision and language tasks.