atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

On Convergence of Nearest Neighbor Classifiers over Feature Transformations

NeurIPS 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Data augmentation and generalization bias · 8 citations (OpenAlex)

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 changedWhereMeasuredEffect
Include the classifier-weight norm alongside MSE (ablation)Analysis of feature transformations for 1NN · Text classification datasetsCorrelation with 1NN errorHelped
Include the classifier-weight norm alongside MSE (ablation)Analysis of feature transformations for 1NN · Computer vision datasetsCorrelation with 1NN errorHelped
Use feature dimension alone to compare transformations (ablation)1NN · Text classification datasetsCorrelation with 1NN errorMixed
Use MSE alone, without the classifier-weight norm (ablation)Analysis of feature transformations for 1NN · Text classification datasetsCorrelation with 1NN errorHurt
Increase the neighborhood size from k=1 to k=8 (ablation)kNN correlation analysis using MSE and norm · SST2CCA score: 0.917 -> 0.97Helped

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