{"ID":2880778,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.13979","arxiv_id":"2508.13979","title":"AutoScale: Linear Scalarization Guided by Multi-Task Optimization Metrics","abstract":"Recent multi-task learning studies suggest that linear scalarization, when using well-chosen fixed task weights, can achieve comparable to or even better performance than complex multi-task optimization (MTO) methods. It remains unclear why certain weights yield optimal performance and how to determine these weights without relying on exhaustive hyperparameter search. This paper establishes a direct connection between linear scalarization and MTO methods, revealing through extensive experiments that well-performing scalarization weights exhibit specific trends in key MTO metrics, such as high gradient magnitude similarity. Building on this insight, we introduce AutoScale, a simple yet effective two-phase framework that uses these MTO metrics to guide weight selection for linear scalarization, without expensive weight search. AutoScale consistently shows superior performance with high efficiency across diverse datasets including a new large-scale benchmark.","short_abstract":"Recent multi-task learning studies suggest that linear scalarization, when using well-chosen fixed task weights, can achieve comparable to or even better performance than complex multi-task optimization (MTO) methods. It remains unclear why certain weights yield optimal performance and how to determine these weights wi...","url_abs":"https://arxiv.org/abs/2508.13979","url_pdf":"https://arxiv.org/pdf/2508.13979v1","authors":"[\"Yi Yang\",\"Kei Ikemura\",\"Qingwen Zhang\",\"Xiaomeng Zhu\",\"Ci Li\",\"Nazre Batool\",\"Sina Sharif Mansouri\",\"John Folkesson\"]","published":"2025-08-19T16:14:00Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[]","has_code":false}