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

TL;DR

This paper presents a versatile active learning framework for regression that accommodates diverse data types and uses Christoffel functions to optimize sampling, demonstrating efficiency in scientific computing applications.

Contribution

It introduces a generalized active learning framework based on Christoffel functions for arbitrary data types and model classes, extending existing methods.

Findings

Near-optimal sample complexity achieved in key cases

Effective in gradient-augmented polynomial learning

Improves data efficiency in MRI and PDE solving

Abstract

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).