AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

Iterative Approximate Cross-Validation

Yuetian Luo, Zhimei Ren, Rina Barber

ICML 2023 · Learning theory and algorithms › Prediction and decision losses · approach: Data attribution and recourse · 0 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 IACV instead of approximate Newton or infinitesimal jackknife during early iterationsGD logistic regression with ridge · Logistic regression with ridge, GDapproximation errorImproved
Use IACV instead of approximate Newton or infinitesimal jackknife during early iterationsGD logistic regression with ridge · Logistic regression with ridge, GDrelative CV errorImproved
Use IACV instead of exact leave-one-out CVGD logistic regression with ridge · Logistic regression with ridge, n=1000runtime speedup: approximately 6-7 times speed-upImproved
Increase sample size from 250 to 1000IACV with GD logistic regression and ridge · Logistic regression with ridge, GDlimiting approximation error: 1.5 \times 10^{-3} to 6.8 \times 10^{-5}Improved
Use IACV instead of approximate Newton or infinitesimal jackknife during early iterationsSGD logistic regression with ridge · Logistic regression with ridge, SGDapproximation errorImproved
Use IACV instead of approximate Newton or infinitesimal jackknife during early iterationsSGD logistic regression with ridge · Logistic regression with ridge, SGDCV errorImproved
Use IACV instead of exact leave-one-out CVSGD logistic regression with ridge · Logistic regression with ridge, SGDruntimeImproved
Use IACV instead of approximate Newton or infinitesimal jackknife during early iterationsProxGD logistic regression with L1 regularization · Logistic regression with L1 regularizer, ProxGDapproximation errorImproved
Use IACV instead of approximate Newton or infinitesimal jackknife during early iterationsProxGD logistic regression with L1 regularization · Logistic regression with L1 regularizer, ProxGDCV errorImproved
Replace IACV with approximate Newton before convergenceGD and ProxGD · Early optimization iterationsapproximation errorHurt

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