The Geometry of Sequential Learning: Lie-Bracket Prediction of Transfer Order

arXiv:2606.24993 · cs.LG · Submitted 2026-06-23 · Read on arXiv

cs.LG

Submitted: 2026-06-23

Updated: 2026-06-23

Terminology

• Accuracy — 2× in this paper · explained in 1 episode
• Adaptation — 1× in this paper · explained in 1 episode
• Domain Adaptation — 1× in this paper · explained in 5 episodes

Sources

• UltraFeedback: Boosting Language Models with Scaled AI Feedback
• The Pile: An 800GB Dataset of Diverse Text for Language Modeling
• HessFormer: Hessians at Foundation Scale
• The Llama 3 Herd of Models
• Sequence Transferability and Task Order Selection in Continual Learning
• Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks