arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2306.00945cs.LGcs.NAmath.NA
收藏

CS4ML:基于 Christoffel 函数的支持任意数据的主动学习通用框架

CS4ML: A general framework for active learning with arbitrary data based on Christoffel functions

Simon Fraser University(西蒙弗雷泽大学);Florida State University(佛罗里达州立大学)

Ben Adcock, Juan M. Cardenas, Nick Dexter

AI总结:

提出 CS4ML 主动学习框架,利用广义 Christoffel 函数优化任意数据类型与非线性模型下的采样测度,实现近最优样本复杂度并验证于科学计算任务。

摘要:

我们提出了一个用于回归问题中主动学习的通用框架。该框架扩展了标准设置,允许使用一般类型的数据,而不仅限于目标函数的逐点样本。这一推广涵盖了许多具有实际意义的情形,例如在变换域中获取的数据(如 Fourier 数据)、向量值数据(如梯度增强数据)、沿连续曲线获取的数据,以及多模态数据(即不同类型测量的组合)。我们的框架考虑依据有限数量的采样测度进行随机采样,并支持任意非线性逼近空间(模型类)。我们引入了广义 Christoffel 函数的概念,并展示如何利用它们优化采样测度。我们证明,在多种重要情形下,这会带来近最优的样本复杂度。本文重点关注科学计算中的应用;在该领域中,由于生成数据通常代价高昂,主动学习往往十分可取。我们通过多项式梯度增强学习、使用生成模型的磁共振成像(MRI),以及利用物理信息神经网络(PINNs)求解 PDE 的自适应采样,展示了该框架的有效性。

英文摘要:

We introduce a general framework for active learning in regression problems. Our framework extends the standard setup by allowing for general types of data, rather than merely pointwise samples of the target function. This generalization covers many cases of practical interest, such as data acquired in transform domains (e.g., Fourier data), vector-valued data (e.g., gradient-augmented data), data acquired along continuous curves, and, multimodal data (i.e., combinations of different types of measurements). Our framework considers random sampling according to a finite number of sampling measures and arbitrary nonlinear approximation spaces (model classes). We introduce the concept of generalized Christoffel functions and show how these can be used to optimize the sampling measures. We prove that this leads to near-optimal sample complexity in various important cases. This paper focuses on applications in scientific computing, where active learning is often desirable, since it is usually expensive to generate data. We demonstrate the efficacy of our framework for gradient-augmented learning with polynomials, Magnetic Resonance Imaging (MRI) using generative models and adaptive sampling for solving PDEs using Physics-Informed Neural Networks (PINNs).

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。

↑