用学习曲线预测改进超参优化，避免误杀潜力选手。
Successive Halving with Learning Curve Prediction via Latent Kronecker Gaussian Processes
- 用潜在克罗内克高斯过程预测学习曲线，指导资源分配
- 实验显示预测法性能接近传统方法但无法超越
- 适合有历史学习曲线数据的场景，提升优化效率
Successive Halving 是一种流行的超参数优化算法，通过逐轮淘汰表现较差的候选者来高效分配计算资源。然而，该方法依赖中间性能值做决策，可能过早淘汰起步慢但最终表现优异的模型。本文研究基于潜在克罗内克高斯过程的学习曲线预测能否克服此问题。在包含多种神经网络架构和点击率预测数据集的大规模实验中，对比了预测驱动与传统性能驱动的策略。结果表明，预测方法虽表现良好，但在资源投入更多时仍不如传统方法，因需完整训练学习曲线作为训练数据。这一缺点可通过利用已有学习曲线数据缓解。
原文摘要 · Abstract (English)
Successive Halving is a popular algorithm for hyperparameter optimization which allocates exponentially more resources to promising candidates. However, the algorithm typically relies on intermediate performance values to make resource allocation decisions, which can cause it to prematurely prune slow starters that would eventually become the best candidate. We investigate whether guiding Successive Halving with learning curve predictions based on Latent Kronecker Gaussian Processes can overcome this limitation. In a large-scale empirical study involving different neural network architectures and a click prediction dataset, we compare this predictive approach to the standard approach based on current performance values. Our experiments show that, although the predictive approach achieves competitive performance, it is not Pareto optimal compared to investing more resources into the standard approach, because it requires fully observed learning curves as training data. However, this downside could be mitigated by leveraging existing learning curve data.
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。