Scholarlink

<p>In this paper, we propose a novel algorithm called adaptive learning &amp; momentum sharpness-aware minimization MAML (AS-MAML) that builds upon the concept of sharpness-aware minimization and adaptive learning and momentum to improve generalization. We prove theoretically by performing convergence analysis and PAC-Bayes analysis that AS-MAML performs better than the state-of-the-art algorithms in model-agnostic meta-learning. We draw the same conclusion through extensive experimental analysis using benchmark datasets.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Using adaptive learning and momentum to improve generalization

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年5月10日

查看全文
  • Usman Anjum,
  • Chris Stockman,
  • Cat Luong,
  • Felix Zhan

摘要

In this paper, we propose a novel algorithm called adaptive learning & momentum sharpness-aware minimization MAML (AS-MAML) that builds upon the concept of sharpness-aware minimization and adaptive learning and momentum to improve generalization. We prove theoretically by performing convergence analysis and PAC-Bayes analysis that AS-MAML performs better than the state-of-the-art algorithms in model-agnostic meta-learning. We draw the same conclusion through extensive experimental analysis using benchmark datasets.