Research map / Learning theory and algorithms / Clustering
Distributed and Provably Good Seedings for k-Means in Constant Rounds
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 |
|---|---|---|---|
| Increase oversampling factor ℓ (with fixed rounds t) in k-means|| seeding | k-means|| seeding (Algorithm 2/3) · theoretical bound (Lemma 4 / Theorem 1) | expected quantization error bound (additive term) | Helped |
| Increase number of rounds t (with fixed oversampling factor ℓ) in k-means|| seeding | k-means|| seeding (Algorithm 2) · theoretical bound (Lemma 4) | expected quantization error bound (additive term) | Helped |
| Use fewer than k-1 rounds of k-means|| (t < k-1) on a hard instance | k-means|| seeding · hard instance construction (Theorem 2) | expected quantization error lower bound relative to Var(X) | Hurt |
Closest papers by meaning
- Fast and Provably Good Seedings for k-Means (NeurIPS 2016 · similarity 0.91)
- Approximate K-Means++ in Sublinear Time (AAAI 2016 · similarity 0.89)
- Fast and Accurate $k$-means++ via Rejection Sampling (NeurIPS 2020 · similarity 0.88)
- A Better k-means++ Algorithm via Local Search (ICML 2019 · similarity 0.87)
- Analyzing $D^\alpha$ seeding for $k$-means (ICML 2024 · similarity 0.86)
- Near-Linear Time Approximation Algorithms for k-means with Outliers (ICML 2024 · similarity 0.81)
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.