AI Paper Atlas

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

A Randomized Algorithm to Reduce the Support of Discrete Measures

Francesco Cosentino, Harald Oberhauser, Alessandro Abate

NeurIPS 2020 · Learning theory and algorithms › Prediction and decision losses · approach: Determinantal point process inference · 6 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 greedy geometric selection of cone-basis points instead of repeated random basis sampling (ablation)Measure reduction algorithm · Synthetic measure reductionrunning timeImproved
Use greedy geometric selection of cone-basis points instead of repeated random basis sampling (ablation)Measure reduction algorithm · Synthetic measure reductionnumber of iterationsImproved
Add Las Vegas resets to the optimized algorithm (ablation)Optimized measure reduction · Synthetic measure reductionrunning timeNo clear effect
Add Las Vegas resets to the randomized algorithm (ablation)Fast least-squares solvers · Real-world datasetsrunning timeImproved
Add divide and conquer to the randomized algorithm (ablation)Fast least-squares solvers · Real-world datasetsrunning-time varianceImproved
Use randomized reduction with deterministic fallback (ablation)Fast least-squares solvers · Real-world datasetsrunning timeImproved
Use the randomized algorithm without a deterministic fallback on highly correlated features (ablation)Fast least-squares solvers · Highly correlated datasetrunning timeHurt
Use randomized reduction in the regime N much larger than nMeasure reduction algorithm · Synthetic measure reductionrunning timeImproved
Run the optimized randomized algorithm without a deterministic fallbackMeasure reduction algorithm · General recombination settingsrunning timeMixed

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