Research map / Label-efficient and robust learning / Knowledge distillation
Self-Distillation Amplifies Regularization in Hilbert Space
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Apply repeated self-distillation | Hilbert-space regularized regression · Illustrative spline regression | fit quality | Mixed |
| Apply repeated self-distillation | ResNet with ℓ2 loss · CIFAR-10 and CIFAR-100 | test accuracy | Mixed |
| Apply repeated self-distillation | ResNet with ℓ2 loss · CIFAR-10 and CIFAR-100 | training accuracy on original labels | Hurt |
| Use cross-entropy instead of ℓ2 loss for distillation (ablation) | ResNet · CIFAR-10 and CIFAR-100 | test accuracy | Mixed |
| Use cross-entropy instead of ℓ2 loss for distillation (ablation) | ResNet · CIFAR-10 and CIFAR-100 | training accuracy on original labels | Hurt |
| Replace self-distillation with early stopping at the same training-loss level (ablation) | ResNet50 · CIFAR-10 | test accuracy | Mixed |
| Use VGG16 instead of ResNet (ablation) | ℓ2 self-distillation · CIFAR-100 | test accuracy | Mixed |
| Lower the training-loss tolerance ε | Self-distillation in regularized regression · Hilbert-space regression | sparsity index | Helped |
Closest papers by meaning
- Dataset Distillation via Knowledge Distillation: Towards Efficient Self-Supervised Pre-training of Deep Networks (ICLR 2025 · similarity 0.89)
- Boost Self-Supervised Dataset Distillation via Parameterization, Predefined Augmentation, and Approximation (ICLR 2025 · similarity 0.88)
- Progressively Knowledge Distillation via Re-parameterizing Diffusion Reverse Process (AAAI 2024 · similarity 0.87)
- The Effect of Optimal Self-Distillation in Noisy Gaussian Mixture Model (NeurIPS 2025 · similarity 0.87)
- Understanding the Gains from Repeated Self-Distillation (NeurIPS 2024 · similarity 0.86)
- Gap Preserving Distillation by Building Bidirectional Mappings with A Dynamic Teacher (ICLR 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.