{"slug": "balanced-adaptive-prototype-selection-for-scalable-tabpfn-inference-on-large", "title": "Balanced Adaptive Prototype Selection for Scalable TabPFN Inference on Large-Scale Tabular Data", "summary": "Researchers introduced Balanced Adaptive Prototype Selection (BAPS), a framework that compresses contexts for TabPFN inference on large-scale tabular data without retraining. Experiments on the million-row HIGGS and SUSY datasets showed that 512 prototypes retain strong predictive performance and reliable calibration, achieving approximately 1,953-fold context compression on an Intel Core i7 CPU with 16 GB RAM and no GPU.", "body_md": "arXiv:2608.12989v1 Announce Type: new\nAbstract: Pretrained tabular foundation models have demonstrated strong predictive capability; however, their application to large-scale datasets remains constrained by the limited inference context. This paper introduces Balanced Adaptive Prototype Selection (BAPS), a framework for constructing compact, information-preserving contexts for scalable TabPFN inference. Without modifying or retraining the pretrained model, BAPS jointly preserves representative structure, informative decision boundaries, local density, class balance, and feature-space diversity. Experiments on the million-row HIGGS and SUSY datasets show that 512 prototypes retain strong predictive performance and reliable calibration, corresponding to an approximately 1,953-fold context compression. All experiments were conducted on an Intel Core i7 CPU with 16 GB RAM and no GPU acceleration. These findings establish effective context construction as a practical mechanism for extending pretrained tabular foundation models to million-scale datasets.", "url": "https://wpnews.pro/news/balanced-adaptive-prototype-selection-for-scalable-tabpfn-inference-on-large", "canonical_source": "https://www.machinebrief.com/news/balanced-adaptive-prototype-selection-for-scalable-tabpfn-in-6ysw", "published_at": "2026-08-14 04:00:00+00:00", "updated_at": "2026-08-14 06:12:47.115917+00:00", "lang": "en", "topics": ["machine-learning", "artificial-intelligence"], "entities": ["TabPFN", "Balanced Adaptive Prototype Selection", "HIGGS", "SUSY", "Intel Core i7"], "alternates": {"html": "https://wpnews.pro/news/balanced-adaptive-prototype-selection-for-scalable-tabpfn-inference-on-large", "markdown": "https://wpnews.pro/news/balanced-adaptive-prototype-selection-for-scalable-tabpfn-inference-on-large.md", "text": "https://wpnews.pro/news/balanced-adaptive-prototype-selection-for-scalable-tabpfn-inference-on-large.txt", "jsonld": "https://wpnews.pro/news/balanced-adaptive-prototype-selection-for-scalable-tabpfn-inference-on-large.jsonld"}}