Functional Compression as Occam's Razor: Algebraic Complexity from Sensitivity Minimization
cs.LG, cond-mat.dis-nn, math.OC, math.RT, stat.ML
Submitted: 2025-11-28
Updated: 2026-11-16
Terminology
Sources
- Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
- Disentangling images with Lie group transformations and sparse coding
- Bispectral Neural Networks
- Representation Learning: A Review and New Perspectives
- The Low-Rank Simplicity Bias in Deep Networks
- Bridging Kolmogorov Complexity and Deep Learning: Asymptotically Optimal Description Length Objectives for Transformers
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis