Endogenous Regime Switching Driven by Scalar-Irreducible Learning Dynamics
Not on the map. Why?
Abstract (arXiv)
Achieving endogenous regime switching is crucial for the emergence of autonomous intelligence, yet remains a central challenge for existing machine learning frameworks, where such transitions are typically externally imposed. In this work, we introduce a classification that distinguishes scalar-reducible dynamics, which can be expressed as gradient flows driven by a scalar objective, from scalar-irreducible dynamics that cannot be reduced to such a form. While most existing machine learning systems operate within the scalar-reducible class, we demonstrate that scalar-irreducible dynamics naturally enable internally generated regime switching through feedback between fast dynamical variables and slow structural adaptation. Using a minimal dynamical model, we illustrate how this mechanism produces sustained endogenous regime transitions without external scheduling. Our results suggest a new dynamical paradigm for regime exploration and provide a potential route toward autonomous learning systems whose adaptive behavior is organized internally rather than externally prescribed.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 12 of its 41 references that are in the map. First posted on arXiv 10 Apr 2026.
Builds on
12 of 41 references.
References · 12
- 2022Generative Adversarial Networkscited by 5,603
- 2014Identifying and attacking the saddle point problem in high-dimensional non-convex optimizationcited by 286
- 2020The large learning rate phase of deep learning: the catapult mechanismcited by 206
- 2015A Differential Equation for Modeling Nesterov's Accelerated Gradient Method: Theory and Insightscited by 203
- 2015Adding Gradient Noise Improves Learning for Very Deep Networkscited by 144
- 2024Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methodscited by 114
- 2017Stochastic gradient descent performs variational inference, converges to limit cycles for deep networkscited by 108
- 2024EfficientTrain++: Generalized Curriculum Learning for Efficient Visual Backbone Trainingcited by 16
- 2022Improving Pre-trained Language Model Fine-tuning with Noise Stability Regularizationcited by 12
- 2022Learning Rate Curriculumcited by 9
- 2022Gradient descent provably escapes saddle points in the training of shallow ReLU networkscited by 5
- 2025LLM-Driven Intrinsic Motivation for Sparse Reward Reinforcement Learningcited by 4
Built on by
Not cited yet.