AI Paper Atlas

Research map / Learning theory and algorithms / Matrix and tensor methods

A determinantal point process for column subset selection

Ayoub Belhadji, Rémi Bardenet, Pierre Chainais

JMLR 2020 · Learning theory and algorithms › Matrix and tensor methods · approach: Structured low-rank learning · 18 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 projection DPP with kernel V_k V_k^T instead of volume samplingcolumn subset selection · Toy datasets (N=100, d=20, k in {3,5})expected Frobenius approximation errorImproved
use projection DPP instead of volume sampling on data with sparse k-leverage scorescolumn subset selection · Basehock vs ColonFrobenius errorImproved
use projection DPP instead of deterministic selection (largest leverage scores, pivoted QR) on near-uniform leverage datacolumn subset selection · ColonFrobenius errorImproved
use double phase instead of projection DPPcolumn subset selection · Colon and BasehockFrobenius errorImproved
apply boosting (repeat 20 times, sample 50 subsets, keep best)randomized CSS algorithms · Colon and BasehockFrobenius errorNo clear effect
use identity (flat) spectrumvolume sampling and projection DPP · Toy datasets, identity spectrumexpected Frobenius error relative to PCAHurt

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