[{"day":"02","OA_type":"free access","OA_place":"publisher","main_file_link":[{"url":"https://doi.org/10.52202/085713-0278","open_access":"1"}],"scopus_import":"1","oa":1,"fulldoi":"https://doi.org/10.52202/085713-0278","acknowledged_ssus":[{"_id":"ScienComp"}],"citation":{"ista":"Zakerinia H, Lampert C. 2025. Fast rate bounds for multi-task and meta-learning with different sample sizes. 39th Conference on Neural Information Processing Systems. NeurIPS: Neural Information Processing Systems, Advances in Neural Information Processing Systems, vol. 38, 9062–9093.","chicago":"Zakerinia, Hossein, and Christoph Lampert. “Fast Rate Bounds for Multi-Task and Meta-Learning with Different Sample Sizes.” In <i>39th Conference on Neural Information Processing Systems</i>, 38:9062–93. Neural Information Processing Systems Foundation, 2025. <a href=\"https://doi.org/10.52202/085713-0278\">https://doi.org/10.52202/085713-0278</a>.","short":"H. Zakerinia, C. Lampert, in:, 39th Conference on Neural Information Processing Systems, Neural Information Processing Systems Foundation, 2025, pp. 9062–9093.","ama":"Zakerinia H, Lampert C. Fast rate bounds for multi-task and meta-learning with different sample sizes. In: <i>39th Conference on Neural Information Processing Systems</i>. Vol 38. Neural Information Processing Systems Foundation; 2025:9062-9093. doi:<a href=\"https://doi.org/10.52202/085713-0278\">10.52202/085713-0278</a>","ieee":"H. Zakerinia and C. Lampert, “Fast rate bounds for multi-task and meta-learning with different sample sizes,” in <i>39th Conference on Neural Information Processing Systems</i>, San Diego, CA, United States, 2025, vol. 38, pp. 9062–9093.","mla":"Zakerinia, Hossein, and Christoph Lampert. “Fast Rate Bounds for Multi-Task and Meta-Learning with Different Sample Sizes.” <i>39th Conference on Neural Information Processing Systems</i>, vol. 38, Neural Information Processing Systems Foundation, 2025, pp. 9062–93, doi:<a href=\"https://doi.org/10.52202/085713-0278\">10.52202/085713-0278</a>.","apa":"Zakerinia, H., &#38; Lampert, C. (2025). Fast rate bounds for multi-task and meta-learning with different sample sizes. In <i>39th Conference on Neural Information Processing Systems</i> (Vol. 38, pp. 9062–9093). San Diego, CA, United States: Neural Information Processing Systems Foundation. <a href=\"https://doi.org/10.52202/085713-0278\">https://doi.org/10.52202/085713-0278</a>"},"publication_identifier":{"issn":["1049-5258"],"isbn":["9798331338275"]},"page":"9062-9093","type":"conference","supplementarymaterial":"yes","department":[{"_id":"GradSch"},{"_id":"ChLa"}],"doi":"10.52202/085713-0278","date_updated":"2026-09-10T08:37:33Z","date_created":"2026-09-06T22:01:59Z","oa_version":"Published Version","corr_author":"1","conference":{"location":"San Diego, CA, United States","end_date":"2025-12-07","start_date":"2025-12-02","name":"NeurIPS: Neural Information Processing Systems"},"user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","month":"12","abstract":[{"text":"We present new fast-rate PAC-Bayesian generalization bounds for multi-task and\r\nmeta-learning in the unbalanced setting, i.e. when the tasks have training sets of\r\ndifferent sizes, as is typically the case in real-world scenarios. Previously, only\r\nstandard-rate bounds were known for this situation, while fast-rate bounds were\r\nlimited to the setting where all training sets are of equal size. Our new bounds\r\nare numerically computable as well as interpretable, and we demonstrate their\r\nflexibility in handling a number of cases where they give stronger guarantees\r\nthan previous bounds. Besides the bounds themselves, we also make conceptual\r\ncontributions: we demonstrate that the unbalanced multi-task setting has different\r\nstatistical properties than the balanced situation, specifically that proofs from\r\nthe balanced situation do not carry over to the unbalanced setting. Additionally,\r\nwe shed light on the fact that the unbalanced situation allows two meaningful\r\ndefinitions of multi-task risk, depending on whether all tasks should be considered\r\nequally important or if sample-rich tasks should receive more weight than samplepoor ones.","lang":"eng"}],"acknowledgement":"This research was supported by the Scientific Service Units (SSU) of ISTA through resources provided by Scientific Computing (SciComp).","language":[{"iso":"eng"}],"status":"public","intvolume":"        38","volume":38,"publication":"39th Conference on Neural Information Processing Systems","publisher":"Neural Information Processing Systems Foundation","article_processing_charge":"No","_id":"22824","das_tickbox":"0","quality_controlled":"1","alternative_title":["Advances in Neural Information Processing Systems"],"date_published":"2025-12-02T00:00:00Z","researchdata_availability":"no","title":"Fast rate bounds for multi-task and meta-learning with different sample sizes","author":[{"last_name":"Zakerinia","first_name":"Hossein","orcid":"0009-0007-3977-6462","full_name":"Zakerinia, Hossein","id":"653bd8b6-f394-11eb-9cf6-c0bbf6cd78d4"},{"id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","full_name":"Lampert, Christoph","first_name":"Christoph","orcid":"0000-0001-8622-7887","last_name":"Lampert"}],"year":"2025","publication_status":"published"}]