AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

Experimental Design for Overparameterized Learning With Application to Single Shot Deep Active Learning

Neta Shoham, Haim Avron

TPAMI 2023 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Normalization and unsupervised meta-learning · 5 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
use bias-oriented criterion t=0 instead of t=0.5 (ablation)greedy overparameterized design · MNIST kernel regression (lambda=0)MSEImproved
use t=0 instead of t=lambda (ablation)greedy overparameterized design · MNIST kernel regression (lambda=0.75^2)MSEImproved
use t=0 instead of t=lambda at lambda=0.001 (ablation)kernel ridge regression design · UCI (112 datasets)datasets with better test error: 5 vs 8, 99 sameNo clear effect
use t=0 instead of t=lambda at lambda=1.0 (ablation)kernel ridge regression design · UCI (112 datasets)datasets with better test error: 21 vs 43, 48 sameImproved
use t=0 instead of t=lambda at lambda=10.0 (ablation)kernel ridge regression design · UCI (112 datasets)datasets with better test error: 19 vs 68, 25 sameImproved
select training set with proposed NTK-based design instead of randomWide-LeNet5 on MNIST · MNIST single shotaccuracy: random needs 600 samples to match 400Improved
select training set with proposed design instead of random on narrow LeNet5LeNet5 on MNIST · MNIST single shotaccuracy: random needs 600 samples to match 400Improved
use wide network instead of narrow LeNet5 (ablation)proposed design and random design · MNIST single shotaccuracyImproved
use sequential uncertainty sampling instead of single shot design with larger training setsLeNet5 on MNIST · MNIST (LeNet5, batch 100)accuracyMixed
use overparameterized OED instead of classical variance-oriented OEDminimum norm linear regression · synthetic linear regression (d=100)test MSEImproved

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