A Shared Learning Rate Is Not a Neutral Control in Selective On-Policy Distillation

arXiv:2609.22109 · cs.LG · Submitted 2026-08-17 · Read on arXiv

cs.LG

Submitted: 2026-08-17

Updated: 2026-08-17

Comments: 16 pages, 3 figures, 6 tables

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Distillation — 2× in this paper · explained in 2 episodes
• On-Policy Distillation — 2× in this paper · explained in 3 episodes
• Ablation — 1× in this paper · explained in 1 episode
• Entanglement — 1× in this paper · explained in 3 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Trace — 1× in this paper · explained in 2 episodes

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: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks