Research map / Learning theory and algorithms / Clustering
Learning-Augmented $k$-means Clustering
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Process neural-network predictor labels with the learning-augmented algorithm | CIFAR-10 clustering · CIFAR-10 | normalized clustering cost: 0.733 -> 0.697 | Helped |
| Use kmeans++ labels as the predictor and process them with the learning-augmented algorithm | CIFAR-10 clustering · CIFAR-10 | normalized clustering cost: 0.640; 13% better | Helped |
| Apply the learning-augmented algorithm to Graph #1 predictor labels | Oregon spectral clustering, k=10 · Oregon graph embeddings, k=10 | clustering cost: 55% | Helped |
| Process randomly corrupted labels with the learning-augmented algorithm | PHY clustering · PHY | clustering cost: roughly a factor of 3x | Helped |
| Increase random label corruption | Oregon Graph #5 predictor · Oregon Graph #5, k=10 | clustering cost | Mixed |
| Use fewer queried predictor labels | Learning-augmented algorithm · CIFAR-10 | clustering cost | Mixed |
Closest papers by meaning
- Improved Learning-augmented Algorithms for k-means and k-medians Clustering (ICLR 2023 · similarity 0.94)
- New Algorithms for the Learning-Augmented k-means Problem (ICLR 2025 · similarity 0.92)
- Learning-Augmented Algorithms for $k$-median via Online Learning (NeurIPS 2025 · similarity 0.88)
- Efficient Constrained K-center Clustering with Background Knowledge (AAAI 2024 · similarity 0.86)
- Average Sensitivity of Hierarchical $k$-Median Clustering (ICML 2025 · similarity 0.86)
- Statistically Optimal $K$-means Clustering via Nonnegative Low-rank Semidefinite Programming (ICLR 2024 · similarity 0.86)
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.