Are Flat Minima an Illusion?
平坦极小值是否只是一个幻觉?
机构 * School of Computing(计算学院) ; The Australian National University(澳大利亚国立大学)
AI总结 本文探讨了平坦极小值对泛化能力的影响,指出弱性才是关键因素,并通过实验验证了弱性与泛化能力的正相关关系。
Comments 27 pages, 1 figure. Major revision adds an affine-invariant joint completion score, PAC-Bayes certificates, a task-alignment theorem, three predeclared 100-network cohorts, a random-label control, and expanded references. Submitted to JMLR