Nabidnur/OPE-means
other model by Nabidnur
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
ARIES series, report #2. OPE-means solves k-means with outliers (choose k centres, drop the z farthest points, minimise the k-means cost of the rest). On the benchmark of OKMeans / OKMeans2 (Jiang & Zhou, NeurIPS 2026), run with the authors' own code on the same machine, OPE-means has a lower robust cost than every one of their algorithms on every one of the 570 paired runs — and its worst seed beats every baseline's best seed on all 10 datasets (4 of them held out). 📄 Technical report: paper/opemeans.pdf · 🧪 Notebooks: notebooks/ · 📒 Full experiment log (25 iterations, negative results included): docs/EXPERIMENTLOG.md † held out: built with the paper's recipe, never used during development. Reductions are paired by seed (mean of 10). "Best baseline" is, per dataset, the baseline with the lowest mean cost among OKMeans, OKMeans2, their FAISS variants, TIKMeans and k-means++. (smallest margin 0.008%, median 2.8%).…
Read the full model card ↗ · Preview checked 2026-11-21T08:48:33.303Z
Inside the original model card — Document outline
- OPE-means — robust k-means without the seed lottery
- Headline results (the paper's 10 seeds, 4 CPU threads, authors' code commit d820666)
- Why OKMeans plays a lottery, and how OPE-means stops it
- Analysis
- Rating (self-assessment, honest)
- Limitations
- Quick start
- Reproduce
- Files
- Citation
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: mit. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
Nabidnur/OPE-means is a other model repository published by Nabidnur on Hugging Face. The source reports the numpy library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- other
- Library
- numpy
- Recent downloads (30 days)
- 0
- Cumulative likes
- 0
- Hugging Face trending score
- 0
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- mit
- Access
- Not gated by Hugging Face
- Created
- 2026-11-21T06:42:50.000Z
- Last modified
- 2026-11-21T06:42:53.000Z
Compatibility and lineage
Language coverage was not reported.
Base-model lineage was not included.
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-11-21T07:02:33.996Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.