Research map / Learning theory and algorithms / Clustering
Minimal Learning Machine: Theoretical Results and Clustering-Based Reference Point Selection
Joonas Hämäläinen, Alisson S. C. Alencar, Tommi Kärkkäinen, César L. C. Mattos, Amauri H. Souza Júnior, João P. P. Gomes
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 |
|---|---|---|---|
| replace random reference points with RS-maximin | MLM with LLS · 15 regression datasets, optimal K | rank sum: 5(54) -> 1(39) | Improved |
| replace random reference points with RS-UPGMA | MLM with LLS · 15 regression datasets, optimal K | rank sum: 5(54) -> 2(40) | Improved |
| replace random reference points with RS-K-means++ | MLM with LLS · 15 regression datasets, optimal K | rank sum: 5(54) -> 4(48) | Improved |
| replace random reference points with RS-maximin | MLM with LLS · S1, K_rel=5 | test RMSE: 0.0366 -> 0.0199 | Improved |
| replace random reference points with RS-maximin | MLM with LLS · S1, K_rel=10 | test RMSE: 0.0188 -> 0.0078 | Improved |
| replace random reference points with RS-maximin | MLM with LLS · BNK, optimal K | test RMSE: 0.0514 -> 0.0481 | Improved |
| replace random reference points with RS-UPGMA | MLM with LLS · CHA, optimal K | test RMSE: 0.0483 -> 0.0403 | Improved |
| replace random reference points with RS-maximin | MLM with LLS · 15 regression datasets, K_rel=5 | rank sum: 5(55) -> 1(33) | Improved |
| replace random reference points with RS-maximin | MLM with LLS · 15 regression datasets, K_rel=40 | rank sum: 5(63) -> 1(31) | Improved |
| replace random reference points with RS-UPGMA | MLM with LLS · CH, K_rel=5 | test RMSE: 0.1201 -> 0.1230 | Hurt |
| replace random reference points with RS-maximin | MLM with LLS · CH, K_rel=10 | test RMSE: 0.1177 -> 0.1212 | Hurt |
| replace random reference points with RS-maximin | MLM with LLS · ALR, K_rel=10 | test RMSE: 0.0417 -> 0.0422 | No clear effect |
Closest papers by meaning
- Data-Efficient Learning via Clustering-Based Sensitivity Sampling: Foundation Models and Beyond (ICML 2024 · similarity 0.84)
- Approximation Vector Machines for Large-scale Online Learning (JMLR 2017 · similarity 0.84)
- Simultaneous Clustering and Model Selection: Algorithm, Theory and Applications (TPAMI 2017 · similarity 0.83)
- Piecewise Constant and Linear Regression Trees: An Optimal Dynamic Programming Approach (ICML 2024 · similarity 0.83)
- Diversified Batch Selection for Training Acceleration (ICML 2024 · similarity 0.82)
- LoRANN: Low-Rank Matrix Factorization for Approximate Nearest Neighbor Search (NeurIPS 2024 · similarity 0.82)
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.
