AI Paper Atlas

Research map / Learning theory and algorithms / Kernels and regression theory

Functional L-Optimality Subsampling for Functional Generalized Linear Models with Massive Data

Hua Liu, Jinhong You, Jiguo Cao

JMLR 2023 · Learning theory and algorithms › Kernels and regression theory · approach: Kernel regression under shift

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 FLoS subsampling instead of full data (n = 10^5, L = 300)functional logistic regression · Simulation I Scenario Icomputing time (s): 4.253 -> 0.036Improved
use FLoS subsampling instead of full data (n = 5x10^6, L = 1000)functional logistic regression · Simulation I Scenario Icomputing time (s): 1107.457 -> 1.348Improved
use FLoS subsampling when full data n = 10^7 exceeds memoryfunctional logistic regression · Simulation I Scenario Ifeasibility: Fail -> 6.571 (L = 3000)Improved
use optimal FLoS probabilities instead of uniform subsamplingsubsampling · Simulation I (RIMSE)RIMSE of functional coefficientImproved
use FLoS probabilities instead of uniform for imbalanced datasubsampling · Simulation I (imbalanced and rare events)RIMSE of functional coefficientImproved
use FLoS instead of uniform subsampling (computing time)subsampling · Simulation I Scenario I, n = 10^7, L = 3000computing time (s): 0.543 -> 6.571Hurt
use FLoS instead of uniform subsampling on kidney transplant datafunctional logistic regression · Kidney transplant (n = 130313)eRIMSE of functional coefficientImproved

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