Research map / Learning theory and algorithms / Clustering
Clustering with Bregman Divergences: an Asymptotic Analysis
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 |
|---|---|---|---|
| Use squared Euclidean (k-means) divergence instead of KL or norm-like divergence for k-centers quantization on uniform [0,1] density | Bregman hard clustering (Lloyd-type) with k=81 · 1-D uniform density on [0,1] | predicted centroid distribution shape (uniform, P1,EU = 1) | No clear effect |
| Use Kullback-Leibler divergence (negative-entropy generator) instead of squared Euclidean | Bregman hard clustering · 2-D uniform density on [0,1]^2, k=81 | centroid distribution shape | Mixed |
| Use norm-like divergence (alpha=3) instead of squared Euclidean | Bregman hard clustering · 2-D uniform density on [0,1]^2, k=81 | centroid distribution shape | Mixed |
Closest papers by meaning
- Bregman Power k-Means for Clustering Exponential Family Data (ICML 2022 · similarity 0.92)
- Modified K-means Algorithm with Local Optimality Guarantees (ICML 2025 · similarity 0.89)
- Learning to Approximate a Bregman Divergence (NeurIPS 2020 · similarity 0.87)
- Simple, Scalable and Effective Clustering via One-Dimensional Projections (NeurIPS 2023 · similarity 0.86)
- Wasserstein $K$-means for clustering probability distributions (NeurIPS 2022 · similarity 0.86)
- The Complexity of k-Means Clustering when Little is Known (ICML 2022 · 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.