AI Paper Atlas

Research map / Label-efficient and robust learning / Knowledge distillation

Knowledge Distillation as Semiparametric Inference

Tri Dao, Govinda M Kamath, Vasilis Syrgkanis, Lester Mackey

ICLR 2021 · Label-efficient and robust learning › Knowledge distillation · approach: Rethinking distillation objectives · 6 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

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 changedWhereMeasuredEffect
Apply cross-fitting instead of vanilla KDRandom forest student and teacher · FICOAUC: up to 4 AUC percentage pointsImproved
Apply loss correction instead of vanilla KDRandom forest student and teacher · Adultstudent performanceImproved
Apply cross-fitting instead of vanilla KDResNet-8 student with ResNet teachers · CIFAR-10accuracy: up to 1.5%Improved
Apply cross-fitting instead of vanilla KDResNet-8 student with ResNet teachers · CIFAR-10cross-entropy test lossImproved
Add loss correction on top of cross-fittingResNet-8 student with ResNet teachers · CIFAR-10accuracyImproved
Add loss correction on top of cross-fittingResNet-8 student with ResNet teachers · CIFAR-10cross-entropy test lossImproved
Vary loss-correction strength from vanilla toward orthogonal correction (ablation)Cross-fit KD with ResNet-8 student and ResNet-20 teacher · CIFAR-10test accuracyMixed
Use a very large loss-correction strength, approaching orthogonal correction (ablation)Cross-fit KD with ResNet-8 student and ResNet-20 teacher · CIFAR-10test accuracyHurt
Use a very large loss-correction strength, approaching orthogonal correction (ablation)Cross-fit KD with ResNet-8 student and ResNet-20 teacher · CIFAR-10training stabilityHurt
Use cross-fitting without loss correction (ablation)Knowledge distillation · Teacher-overfitting settingsstudent errorImproved
Use cross-fitting without loss correction (ablation)Knowledge distillation · Teacher-underfitting settingsstudent errorNo clear effect

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy