English

Learning Functional Transduction

Machine Learning 2023-05-19 v2 Neural and Evolutionary Computing

Abstract

Research in machine learning has polarized into two general approaches for regression tasks: Transductive methods construct estimates directly from available data but are usually problem unspecific. Inductive methods can be much more specific but generally require compute-intensive solution searches. In this work, we propose a hybrid approach and show that transductive regression principles can be meta-learned through gradient descent to form efficient in-context neural approximators by leveraging the theory of vector-valued Reproducing Kernel Banach Spaces (RKBS). We apply this approach to function spaces defined over finite and infinite-dimensional spaces (function-valued operators) and show that once trained, the Transducer can almost instantaneously capture an infinity of functional relationships given a few pairs of input and output examples and return new image estimates. We demonstrate the benefit of our meta-learned transductive approach to model complex physical systems influenced by varying external factors with little data at a fraction of the usual deep learning training computational cost for partial differential equations and climate modeling applications.

Keywords

Cite

@article{arxiv.2302.00328,
  title  = {Learning Functional Transduction},
  author = {Mathieu Chalvidal and Thomas Serre and Rufin VanRullen},
  journal= {arXiv preprint arXiv:2302.00328},
  year   = {2023}
}
R2 v1 2026-06-28T08:28:54.679Z