What Do Students Learn? A Feature-Level Analysis of Dark Knowledge

arXiv:2606.03052 · cs.LG · Submitted 2026-06-02 · Read on arXiv

cs.LG

Submitted: 2026-06-02

Updated: 2026-09-01

Terminology

• Distillation — 60× in this paper · explained in 2 episodes
• Knowledge Distillation — 18× in this paper · explained in 11 episodes
• Self-Distillation — 15× in this paper · explained in 7 episodes
• Confusion Distillation — 13× in this paper
• Regularization — 9× in this paper · explained in 3 episodes
• Generalization — 5× in this paper · explained in 13 episodes
• Loss Function — 5× in this paper · explained in 2 episodes
• Representation Learning — 5× in this paper · explained in 2 episodes
• Accuracy — 3× in this paper · explained in 1 episode
• Computer Vision and Pattern Recognition — 3× in this paper
• Attention Transfer — 2× in this paper
• Cosine Similarity — 2× in this paper · explained in 3 episodes
• Exponential Moving Average — 2× in this paper
• In International Conference on Learning Representations — 2× in this paper
• In International Conference on Machine Learning — 2× in this paper
• Alignment — 1× in this paper · explained in 1 episode
• Alternation — 1× in this paper · explained in 1 episode
• CVF International Conference on Computer Vision — 1× in this paper
• Clustering — 1× in this paper · explained in 2 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Core — 1× in this paper · explained in 2 episodes
• Data Augmentation — 1× in this paper · explained in 7 episodes
• Exponential Moving Average (EMA) — 1× in this paper · explained in 2 episodes
• Interpretability — 1× in this paper · explained in 15 episodes

Sources

• Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
• Understanding and Improving Knowledge Distillation

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