论文标题
部分可观测时空混沌系统的无模型预测
Training Data Influence Analysis and Estimation: A Survey
论文作者
论文摘要
好的模型需要良好的培训数据。对于过度参数的深层模型，训练数据和模型预测之间的因果关系越来越不透明，并且了解不足。影响分析通过量化每个培训实例的数量改变了最终模型，从而部分揭开了培训的基本相互作用。在最坏的情况下，准确地测量培训数据的影响可能很难；这导致了影响估计量的发展和使用，这仅近似真正的影响。本文提供了培训数据影响分析和估计的首次全面调查。我们首先将培训数据影响的各种和正交定义的定义正式化。然后，我们将最先进的影响分析方法组织成分类法。我们详细描述了每种方法，并比较它们的基本假设，渐近复杂性以及整体优势和缺点。最后，我们提出了未来的研究方向，以使影响分析在实践以及理论上和经验上更加有用。可以在https://github.com/zaydh/influence_analsisy_papers上获得与影响分析有关的策划，最新的资源清单。
Good models require good training data. For overparameterized deep models, the causal relationship between training data and model predictions is increasingly opaque and poorly understood. Influence analysis partially demystifies training's underlying interactions by quantifying the amount each training instance alters the final model. Measuring the training data's influence exactly can be provably hard in the worst case; this has led to the development and use of influence estimators, which only approximate the true influence. This paper provides the first comprehensive survey of training data influence analysis and estimation. We begin by formalizing the various, and in places orthogonal, definitions of training data influence. We then organize state-of-the-art influence analysis methods into a taxonomy; we describe each of these methods in detail and compare their underlying assumptions, asymptotic complexities, and overall strengths and weaknesses. Finally, we propose future research directions to make influence analysis more useful in practice as well as more theoretically and empirically sound. A curated, up-to-date list of resources related to influence analysis is available at https://github.com/ZaydH/influence_analysis_papers.
