Get Started
Research questionHow does coordinate-basis choice affect the complexity and learnability of equivalent finite-field inversion?Different coordinate bases can represent the same inversion operation while producing Boolean formulations with different structure. Mathematical equivalence therefore does not guarantee equal difficulty for a learned representation.
AI
Machine Learning
Research Paper
Latest papersRecent research connected to this question, newest first.Representation Redundancy and Structural Complexity in Finite-Field InversionThe source proves when ordered bases induce the same coordinate inversion map through Galois orbits, analyzes several Boolean formulations, and uses exhaustive calculations and multilayer-perceptron experiments to compare structural complexity and learning behavior. Its empirical conclusions are limited to finite-field inversion, the tested formulations, and the tested model settings.research paper · Sep 4, 2026
Related questions
How does restricting complex-valued neural networks to real pre-activations change asymptotic storage capacity?How should frequency-based smoothness be defined on non-abelian groups without a canonical ordering of irreducible representations?Can one squared-loss estimator achieve both minimax and universal exponential rates for finite versus countably infinite hypothesis classes?What can finite threshold networks represent, and how do recurrence and invariance constrain that computation?
Home
Topics
Search
Library