Phase Transitions & ML
Background on phase transitions
Relevant Workshops
Papers
Grokking
Benign Overfitting and Grokking in ReLU Networks for XOR Cluster Data
Droplets of Good Representations: Grokking as a First Order Phase Transition in Two Layer Networks
Grokking as the Transition from Lazy to Rich Training Dynamics
Predicting Grokking Long Before it Happens: A look into the loss landscape of models which grok
Progress measures for grokking via mechanistic interpretability
Grokking phase transitions in learning local rules with gradient descent
Towards Understanding Grokking: An Effective Theory of Representation Learning
Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets
Phase transitions in computation
More examples: Jacob Steinhardt's blog: Future ML Systems Will Be Qualitatively Different - LessWrong
Phase Transitions in AI (Irina Rish) at Neural Scaling workshop
Tutorial on Phase Transitions by Guillaume Dumas video (chapter 2) slides (same workshop)
The statistical mechanics of learning a rule
Computation at the edge of chaos: Phase transitions and emergent computation
Statistical Mechanics of Deep Learning
Extended critical regimes of deep neural networks
A PHASE TRANSITION FOR REPEATED AVERAGES
A Mathematical Framework for Transformer Circuits
Machine Learning Methods for Phase Transition Analysis and Prediction
Phase Transitions in (Natural) Complex Systems
How critical is brain criticality?
Unveiling phase transitions with machine learning
Machine learning dynamical phase transitions in complex networks
Phase transitions and critical behavior in human bimanual coordination
A universal scaling law between gray matter and white matter of cerebral cortex
Long-Range Temporal Correlations and Scaling Behavior in Human Brain Oscillations
Power-Law Scaling in the Brain Surface Electric Potential
Phase transitions in the assembly of multivalent signaling proteins
A theoretical model of phase transitions in human hand movements
SOC
Self-organized criticality as a fundamental property of neural systems
Does the $1/f$ Frequency Scaling of Brain Signals Reflect Self-Organized Critical States?