突破传统假设，让主动学习在模型不准确时仍有效。
Active Learning via Regression Beyond Realizability
- 用凸模型类代替理想可实现性假设，放宽适用条件。
- 在非可实现场景下仍保持相近的标签与样本复杂度。
- 适合实际中模型可能错误设定的主动学习任务。
我们提出一种基于代理风险最小化的多分类主动学习新框架，该框架摆脱了标准可实现性假设的限制。现有基于代理的主动学习算法严重依赖可实现性——即最优代理预测器存在于模型类别中——这限制了其在实际中模型误设情况下的应用。本文证明，在远弱于可实现性的条件下，只要考虑的模型类是凸的，仍可获得与先前工作相当的标签复杂度和样本复杂度。尽管达到相似率，先前方法在某些非可实现但本假设成立的情况下会失效。我们的分轮主动学习算法通过每轮在全模型类上拟合查询数据，并聚合这些模型得到一个非正规分类器，从而区别于以往方法。
原文摘要 · Abstract (English)
We present a new active learning framework for multiclass classification based on surrogate risk minimization that operates beyond the standard realizability assumption. Existing surrogate-based active learning algorithms crucially rely on realizability$\unicode{x2014}$the assumption that the optimal surrogate predictor lies within the model class$\unicode{x2014}$limiting their applicability in practical, misspecified settings. In this work we show that under conditions significantly weaker than realizability, as long as the class of models considered is convex, one can still obtain a label and sample complexity comparable to prior work. Despite achieving similar rates, the algorithmic approaches from prior works can be shown to fail in non-realizable settings where our assumption is satisfied. Our epoch-based active learning algorithm departs from prior methods by fitting a model from the full class to the queried data in each epoch and returning an improper classifier obtained by aggregating these models.
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。