Research map / Label-efficient and robust learning / Knowledge distillation
Bayesian Optimization Meets Self-Distillation
HyunJae Lee, Heon Song, Hyeonsoo Lee, Gi-hyeon Lee, Suyeong Park, Donggeun Yoo
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| initialize both student and teacher from pretrained trial models instead of neither (ablation) | BOSS · CIFAR-100 (VGG-16) | top-1 accuracy (%): 76.48 -> 77.69 | Improved |
| initialize only the student from pretrained weights (ablation) | BOSS · CIFAR-100 (VGG-16) | top-1 accuracy (%): 76.48 -> 76.93 | Improved |
| initialize teacher and student from different pretrained models instead of the same one | single-round SD, VGG-16 on CIFAR-100 · CIFAR-100 (VGG-16) | top-1 accuracy (%) | Improved |
| combine SD with BO rather than BO alone | TPE-based BO · CIFAR-100 (VGG-16) | top-1 accuracy (%): 76.48 -> 77.69 | Improved |
| replace TPE with GP in BOSS (ablation) | BOSS · CIFAR-100 (VGG-16) | top-1 accuracy (%): 75.69 -> 77.36 | Improved |
| add SMAC variant of BOSS (ablation) | SMAC BO · CIFAR-100 (VGG-16) | top-1 accuracy (%): 75.93 -> 77.54 | Improved |
| use different distillation losses (KL, FitNets, Attention) inside BOSS (ablation) | BOSS · CIFAR-100 (VGG-16) | top-1 accuracy (%): SD 76.08 -> 77.69 (MSE); 75.63 -> 77.32 (KL) | Improved |
| add BOSS under stronger augmentation (AutoAugment, Cutout) | VGG-16 · CIFAR-100 (VGG-16, AutoAugment+Cutout) | top-1 accuracy (%): 78.07 -> 80.81 | Improved |
| use K=8 candidates instead of smaller or larger K | BOSS · CIFAR-100 (VGG-16) | top-1 accuracy (%) | Improved |
| vary number of warm-up trials W (best at 32) | BOSS · CIFAR-100 (VGG-16) | top-1 accuracy (%) | No clear effect |
| apply SD alone or BO alone under high label noise | VGG-16 CIFAR-100 noisy labels · CIFAR-100 noisy labels | top-1 accuracy (%) | Mixed |
Closest papers by meaning
- Boost Self-Supervised Dataset Distillation via Parameterization, Predefined Augmentation, and Approximation (ICLR 2025 · similarity 0.87)
- The Effect of Optimal Self-Distillation in Noisy Gaussian Mixture Model (NeurIPS 2025 · similarity 0.87)
- Efficient Hyperparameter Optimization with Adaptive Fidelity Identification (CVPR 2024 · similarity 0.86)
- Bayesian Optimisation with Unknown Hyperparameters: Regret Bounds Logarithmically Closer to Optimal (NeurIPS 2024 · similarity 0.86)
- Bayesian Knowledge Distillation: A Bayesian Perspective of Distillation with Uncertainty Quantification (ICML 2024 · similarity 0.86)
- High-Dimensional Bayesian Optimization via Semi-Supervised Learning with Optimized Unlabeled Data Sampling (ICML 2024 · 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.
