AI Paper Atlas

Research map / Learning theory and algorithms / Clustering

Active Learning with Low-Rank Structure for Data Selection

Vincent Cohen-Addad, Sasidhar Kunapuli, Vahab Mirrokni, Mahdi Nikdan, David Woodruff, Samson Zhou

ICML 2026 · Learning theory and algorithms › Clustering · approach: Coresets and dynamic clustering · 0 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 leverage score sampling to choose basis samples instead of uniform (ablation)Low-rank SS · ViGGO Qwen2.5-3B 12.5%accuracy (%): 50.70 -> 51.54Improved
use leverage score sampling instead of k-medians basis selection (ablation)Low-rank SS · ViGGO Qwen2.5-3B 12.5%accuracy (%): 45.80 -> 51.54Improved
select subsets with Llama3-8B instead of Qwen2.5-3B itselfLow-rank SS · ViGGO Qwen2.5-3B 12.5%accuracy (%): 51.54 -> 55.74Improved
replace clustering-based SS with low-rank SSSensitivity sampling · ViGGO Qwen2.5-3B 25%accuracy (%): 71.57 -> 75.91Improved
replace clustering-based SS with low-rank SSSensitivity sampling · ViGGO Llama3-8B 25%accuracy (%): 86.6 ± 2.8 -> 88.3 ± 0.2Improved
replace clustering-based SS with low-rank SSSensitivity sampling · GSM8k Llama3-8B 25%accuracy (%): 70.2 -> 68.4Hurt
replace clustering-based SS with low-rank SSSensitivity sampling · ViGGO Llama3-8B 12.5%accuracy (%): 72.8 -> 69.7Hurt
replace clustering-based SS with low-rank SSSensitivity sampling · SQL Llama3-8B 6.25%accuracy (%): 68.3 -> 70.4Improved
replace uniform sampling with low-rank SSData selection · Average over datasets Llama3-8B 6.25%accuracy (%): 52.0 -> 54.9Improved
replace uniform sampling with low-rank SS at 12.5% averageData selection · Average over datasets Llama3-8B 12.5%accuracy (%): 69.2 -> 70.4Improved
replace loss with gradient norm as sensitivity objective and BERT with GTR embeddingsLow-rank SS · GSM8k Llama3-8B 12.5%validation accuracyNo 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