AI Paper Atlas

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

Censored Quantile Regression Neural Networks for Distribution-Free Survival Analysis

Tim Pearce, Jong-Hyeon Jeong, yichen jia, Jun Zhu

NeurIPS 2022 · Learning theory and algorithms › Prediction and decision losses · approach: Probabilistic calibration · 3 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
replace sequential per-quantile NN grid with single-NN CQRNNcensored quantile regression NN · Norm linear, 9 quantilestraining speed up: 14.7$\times$Improved
replace sequential grid with CQRNN, 19 quantilescensored quantile regression NN · Norm sametraining speed up: 34.3$\times$Improved
replace sequential grid with CQRNNcensored quantile regression NN · type 1 datasetsparameter saving: 8.3$\times$ (9 quantiles), 16.2$\times$ (19 quantiles)Improved
replace sequential grid with CQRNNcensored quantile regression NN · 14 type 1 datasetsTQMSE: 8/14 CQRNN better, 3/14 seq. grid betterMixed
CQRNN vs sequential gridcensored quantile regression NN · Norm linearTQMSE: 2.779 -> 0.088Improved
CQRNN vs excluding censored pointscensored quantile regression NN · Norm linearTQMSE: 0.566 -> 0.088Improved
CQRNN vs DeepQuantRegcensored quantile regression NN · Norm linearTQMSE: 1.172 -> 0.088Improved
CQRNN vs LogNorm MLEcensored quantile regression NN · Norm linearTQMSE: 0.184 -> 0.088Improved
CQRNN vs sequential grid on Norm uniformcensored quantile regression NN · Norm uniformTQMSE: 0.175 $\pm$ 0.033Hurt
CQRNN vs sequential gridcensored quantile regression NN · type 3 datasetsC-index and CensDCal: 4/7 C-index, 7/7 CensDCalImproved
larger quantile grid M in {9,19,39} (ablation)CQRNN · type 1 datasetsTQMSEMixed
set y* to 1.2 times the max training y (ablation)CQRNN · benchmarksaccuracy of quantilesNo 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