Research map / Learning theory and algorithms / Clustering
Provable Variable Selection for Streaming Features
Jing Wang, Jie Shen, Ping Li
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 changed | Where | Measured | Effect |
|---|---|---|---|
| use online leverage-score feature selection (OFS) instead of Laplacian score | LapS · CIFAR-10 | CPU time: 2 mins -> 2.28 | Improved |
| use OFS instead of Alpha-investing | Alpha · CIFAR-10 | CPU time: 3 mins -> 2.28 | Improved |
| use OFS instead of Alpha-investing | Alpha · AR | CPU time: 26.99 -> 1.74 | Improved |
| use OFS instead of LevS | LevS · AR | CPU time: 7.76 -> 1.74 | Improved |
| use OFS instead of LapS | LapS · MNIST | CPU time: 19.38 -> 1.32 | Improved |
| use OFS instead of LevS | LevS · USPS | CPU time: 0.94 -> 0.15 | Improved |
| use OFS instead of SEC | SEC · all six datasets | CPU time: 0.002 to 0.005 versus 0.05 to 2.28 | Hurt |
| use OFS instead of LapS on ORL | LapS · ORL | CPU time: 0.24 -> 0.05 | Improved |
| use OFS instead of Alpha on ORL | Alpha · ORL | CPU time: 0.42 -> 0.05 | Improved |
| cluster on OFS-selected feature subset (10 to 500 features) instead of all features | k-means on all features · COIL20, CIFAR-10, ORL | clustering accuracy | Improved |
| use OFS instead of baseline feature selection methods across 10 to 500 selected features | LapS, LevS, Alpha, SEC · COIL20, CIFAR-10, ORL | clustering accuracy | Improved |
| process features one at a time online using a skinny sketch matrix instead of the full data matrix | batch methods · CIFAR-10 | CPU time | Improved |
Closest papers by meaning
- Adaptive Sparse Confidence-Weighted Learning for Online Feature Selection (AAAI 2019 · similarity 0.87)
- Data-Efficient Learning via Clustering-Based Sensitivity Sampling: Foundation Models and Beyond (ICML 2024 · similarity 0.85)
- SAND: One-Shot Feature Selection with Additive Noise Distortion (ICML 2025 · similarity 0.85)
- Consensus Guided Unsupervised Feature Selection (AAAI 2016 · similarity 0.85)
- Most Influential Subset Selection: Challenges, Promises, and Beyond (NeurIPS 2024 · similarity 0.83)
- Contextual Feature Selection with Conditional Stochastic Gates (ICML 2024 · similarity 0.83)
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.
