Backend
Equivariant Modeling with Polynomial Features via Minimal Homogeneous Generators
arXiv stat.ML0 views
arXiv:2611.24896v1 Announce Type: cross Abstract: We present a general framework for modeling and learning equivariant functions between finite dimensional semisimple real group representations, unifying constructions developed across many application areas. Our model is a linear combination of equivariant polynomial features whose coefficients are arbitrary learnable functions of invariant polynomial features. We take as features minimal homogeneous generators for the invariant algebra and the covariant module over the invariant algebra, up to prescribed degrees. We provide a Python package that automatically computes these features and fits the resulting models to training data. The algorithm for feature computation requires explicit isotypic decompositions of the input and output representations, along with explicit Clebsch-Gordan decompositions of the tensor product of irreducible representations, and achieves speedups over alternative methods in computational algebra. Numerical experiments in scientific modeling demonstrate the full learning pipeline and yield accurate predictors with few trainable parameters, using the model both for end-to-end prediction and within layers of larger architectures.
Source:https://arxiv.org/abs/2611.24896PreviousCounterfactual World Models: JEPAs That Reason About "What If"NextWhen Features Beat Noise: A Noise-Driven Hypothesis Testing Method for Feature Selection
Related posts
Vercel Board: A Message Board Built for Agent Swarms
0dev.to

GTA VI: 212 GB, Pre-Load and What Take-Two Says About AI
0dev.to

Discord bot offline a week while systemd said active: a plugin timeout
0dev.to
Your AI Bill Has a Second Price Dial — and It Can Out-Swing Model Choice
0dev.to
Bitbucket Data Center Counts Point to a Repository Service With a Separate Admin Boundary
0dev.to

pgvector HNSW Filtering: 431 of 2,000 LIMIT 10 Queries Came Back Short
0dev.to