用强化学习动态选样本,让模型学得更快更准。
Bandit Guided Submodular Curriculum for Adaptive Subset Selection
- 把选样本变成多臂赌博机问题,用子模函数当选择策略。
- 在图像和语言数据集上准确率更高,效率也更好。
- 适合需要高效训练的场景,尤其擅长自动调优学习顺序。
传统课程学习从简单样本开始,但难度定义始终模糊。已有工作用子模函数生成难度评分,我们重新诠释自适应子集选择,将其建模为多臂赌博机问题:每条臂对应一个子模函数,用于指导样本选择。本文提出ONLINESUBMOD,一种新型在线贪心策略,以效用驱动奖励为目标,可在多种采样环境下实现无遗憾性能。实验表明,ONLINESUBMOD在视觉与语言数据集上均优于传统课程学习和双层优化方法,展现出更优的准确率-效率平衡。更广泛地,我们证明验证驱动的奖励度量可为课程调度提供理论依据。
原文摘要 · Abstract (English)
Traditional curriculum learning proceeds from easy to hard samples, yet defining a reliable notion of difficulty remains elusive. Prior work has used submodular functions to induce difficulty scores in curriculum learning. We reinterpret adaptive subset selection and formulate it as a multi-armed bandit problem, where each arm corresponds to a submodular function guiding sample selection. We introduce ONLINESUBMOD, a novel online greedy policy that optimizes a utility-driven reward and provably achieves no-regret performance under various sampling regimes. Empirically, ONLINESUBMOD outperforms both traditional curriculum learning and bi-level optimization approaches across vision and language datasets, showing superior accuracy-efficiency tradeoffs. More broadly, we show that validationdriven reward metrics offer a principled way to guide the curriculum schedule.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。