vPALs：迈向面向资源管理的可验证性能感知学习系统
vPALs: Towards Verified Performance-aware Learning System For Resource Management
AI总结：
vPALs通过结合相关系统指标与验证机制，在运行时为集群资源管理提供安全的性能预测，解决普通神经网络易受分布外样本影响的问题，并在基准测试中优于普通神经网络。
摘要：
在集群中运行时准确预测任务性能，对于资源管理系统判断任务是否因干扰导致的性能下降而需要迁移具有优势。这对集群运营商和服务所有者都有益。然而，部署采用学习方法的性能预测系统需要复杂的保障机制，因为这些模型（如深度神经网络（DNNs））具有固有的随机性和黑箱特性。普通神经网络（NNs）可能容易受到分布外数据样本的影响，从而导致次优决策。为了在性能预测中迈向安全的学习系统，我们提出了vPALs，它利用高度相关的系统指标和验证来在运行时产生安全的性能预测，为将学习技术集成到集群资源管理系统中提供额外的安全层。我们的实验表明，在我们的基准工作负载上，vPALs能够优于普通神经网络。
英文摘要：
Accurately predicting task performance at runtime in a cluster is advantageous for a resource management system to determine whether a task should be migrated due to performance degradation caused by interference. This is beneficial for both cluster operators and service owners. However, deploying performance prediction systems with learning methods requires sophisticated safeguard mechanisms due to the inherent stochastic and black-box natures of these models, such as Deep Neural Networks (DNNs). Vanilla Neural Networks (NNs) can be vulnerable to out-of-distribution data samples that can lead to sub-optimal decisions. To take a step towards a safe learning system in performance prediction, We propose vPALs that leverage well-correlated system metrics, and verification to produce safe performance prediction at runtime, providing an extra layer of safety to integrate learning techniques to cluster resource management systems. Our experiments show that vPALs can outperform vanilla NNs across our benchmark workload.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
