Scholarlink

<p>In this paper, we propose Adjusted Shuffling SARAH, a novel algorithm that integrates shuffling strategies into the recursive SARAH framework using a dynamic weighting mechanism to enhance exploration. We analyze the algorithm under two operating modes. First, we show that the Exact Mode matches the best-known theoretical guarantees for shuffling variance-reduced methods in both strongly convex and non-convex settings. Second, to address large-scale regimes, we introduce an Inexact Mode that utilizes mini-batch estimators. A key contribution of our work is proving that this Inexact Mode achieves a total complexity independent of the dataset size, making it significantly more scalable than existing shuffling methods when the sample size is large.</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

Adjusted Shuffling SARAH: Advancing Complexity Analysis via Dynamic Gradient Weighting

  • 期刊论文

  • 发表日期：

    2026年6月22日

查看全文
  • Duc Toan Nguyen,
  • Trang H. Tran,
  • Lam M. Nguyen

摘要

In this paper, we propose Adjusted Shuffling SARAH, a novel algorithm that integrates shuffling strategies into the recursive SARAH framework using a dynamic weighting mechanism to enhance exploration. We analyze the algorithm under two operating modes. First, we show that the Exact Mode matches the best-known theoretical guarantees for shuffling variance-reduced methods in both strongly convex and non-convex settings. Second, to address large-scale regimes, we introduce an Inexact Mode that utilizes mini-batch estimators. A key contribution of our work is proving that this Inexact Mode achieves a total complexity independent of the dataset size, making it significantly more scalable than existing shuffling methods when the sample size is large.