CS4ML: A general framework for active learning with arbitrary data based on Christoffel functions
This work addresses the need for efficient data acquisition in scientific computing, where generating data is costly, by providing a flexible active learning framework, though it is incremental as it builds on existing Christoffel function concepts.
The authors tackled the problem of active learning in regression by introducing a general framework that accommodates arbitrary data types, such as transform domain and multimodal data, and proved near-optimal sample complexity in key cases. They demonstrated effectiveness in applications like gradient-augmented learning and MRI using generative models.
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).