AI Paper Atlas

Research map / Optimization / Optimizers

Scaling-up Empirical Risk Minimization: Optimization of Incomplete $U$-statistics

Stephan Clémençon, Igor Colin, Aurélien Bellet

JMLR 2016 · Optimization › Optimizers · approach: Stochastic gradient MCMC · 32 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 complete U-statistic with incomplete U-statistic (same pair budget) in one-time samplingERM for metric learning · Synthetic metric learningsubsample size p to reach 5% of optimum risk: p = 50 vs p > 80Improved
replace complete U-statistic with incomplete U-statistic in one-time samplingERM for metric learning · MNIST metric learningtest riskImproved
use incomplete U-statistic mini-batches instead of complete ones in SGDSGD metric learning · MNIST metric learning (mini-batch sizes 10 to 253)test riskImproved
use incomplete U-statistic instead of complete one for clustering riskmodel selection · Forest cover type clusteringmodel selection time (s): 66 -> 0.1Improved
use incomplete U-statistic with B=5,000 instead of complete riskmodel selection · Forest cover type clusteringselected model: P8 selected by bothNo clear effect
use incomplete U-statistic instead of complete U-statistic on subsample (same pair count)model selection · Forest cover type clusteringcorrect model selection: 57% -> 100 of 100 seedsImproved
increase mini-batch sizeSGD-Incomplete vs SGD-Complete · MNIST metric learninggap between variants: gap shrinks as m growsHurt

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