AI Paper Atlas

Research map / Optimization / Implicit bias and generalization

Towards Understanding Knowledge Distillation

Mary Phuong, Christoph Lampert

ICML 2019 · Optimization › Implicit bias and generalization · approach: In-context learning as gradient descent

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
distillation-trained linear student with n >= d training points (exact recovery of teacher weights)linear distillation (N=1, gradient flow from zero init) · theoretical, linear binary classificationexpected transfer riskImproved
increase transfer set size from n < d to n >= dlinear distillation student · theoretical, linear binary classificationexpected transfer riskImproved
favorable data geometry (higher angular alignment, kappa) instead of low alignment (ablation)linear distillation student · synthetic polynomial-angle tasks, d=1000, n=20transfer riskImproved
gradient-descent optimization bias (small δ) instead of treating all minimizers equally (large δ) (ablation)linear distillation student · MNIST digits 0 vs 1, n=100transfer riskImproved
higher monotonicity index of the learner (negative correlation with transfer risk) (ablation)distillation and hard-target learners · polynomial-angle task, d=100, n=5transfer riskNo 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