{"@context":"https://schema.org","@type":"CreativeWork","@id":"https://froggit.ai/public/capsules/f5efbddb-a5ae-4c85-9546-d4bce6a7300f","identifier":"f5efbddb-a5ae-4c85-9546-d4bce6a7300f","url":"https://froggit.ai/public/capsules/f5efbddb-a5ae-4c85-9546-d4bce6a7300f","name":"Spend Less, Fit Better: Budget-Efficient Scaling Law Fitting via Active Experiment Selection","text":"# Spend Less, Fit Better: Budget-Efficient Scaling Law Fitting via Active Experiment Selection\n\nSource-backed public reference for arXiv:2604.22753.\n\n**Authors:** Sijie Li, Shanda Li, Haowei Lin, Weiwei Sun, Ameet Talwalkar, Yiming Yang\n**Primary source:** https://arxiv.org/abs/2604.22753\n**Published:** 2026-04-24T17:59:42Z\n**Updated:** 2026-04-24T17:59:42Z\n**Categories:** cs.LG\n\n## Abstract Summary\nScaling laws are used to plan multi-million-dollar training runs, but fitting those laws can itself cost millions. In modern large-scale workflows, assembling a sufficiently informative set of pilot experiments is already a major budget-allocation problem rather than a routine preprocessing step. We formulate scaling-law fitting as budget-aware sequential experimental design: given a finite pool of runnable experiments with heterogeneous costs, choose which runs to execute so as to maximize extrapolation accuracy in a high-cost target region. We then propose an uncertainty-aware method for sequentially allocating experimental budget toward the runs most useful for target-region extrapolation. Across a diverse benchmark of scaling-law tasks, our method consistently outperforms classical design-based baselines, and often approaches the performance of fitting on the full experimental set while using only about 10% of the total training budget. Our code is available at https://github.com/PlanarG/active-sl.\n\n## Public Use Notes\n- This capsule summarizes the paper's arXiv metadata and abstract; it is not an independent replication or endorsement of the paper's claims.\n- Use it as a cited research reference for discovery, retrieval, and agent context.\n- For clinical, security, operational, or deployment-sensitive topics, treat the paper as research context rather than medical, legal, safety, or engineering advice.\n\n## Source\n- https://arxiv.org/abs/2604.22753","keywords":["cs.LG"],"about":[],"citation":["https://arxiv.org/abs/2604.22753"],"isPartOf":{"@type":"Dataset","name":"Forge Cascade Knowledge Graph","url":"https://froggit.ai"},"publisher":{"@type":"Organization","name":"Forge Cascade","url":"https://froggit.ai"},"dateCreated":"2026-04-27T06:00:02.651000Z","dateModified":"2026-06-19T03:17:48Z","isBasedOn":"https://arxiv.org/abs/2604.22753","additionalProperty":[{"@type":"PropertyValue","name":"trust_level","value":100},{"@type":"PropertyValue","name":"verification_status","value":"sources_verified"},{"@type":"PropertyValue","name":"provenance_status","value":"valid"},{"@type":"PropertyValue","name":"evidence_level","value":"primary_source"},{"@type":"PropertyValue","name":"content_hash","value":"0532b05e3caf37362406185403f3c5286e03560d8ac1d200b753697d107e37de"}]}