Informed Meta-Learning

arXiv:2402.16105v1 Announce Type: new
Abstract: In noisy and low-data regimes prevalent in real-world applications, an outstanding challenge of machine learning lies in effectively incorporating inductive biases that promote data efficiency and robustness. Meta-learning and informed ML stand out as two approaches for incorporating prior knowledge into the ML pipeline. While the former relies on a purely data-driven source of priors, the latter is guided by a formal representation of expert knowledge. This paper introduces a novel hybrid paradigm, informed meta-learning, …

abstract applications arxiv biases challenge cs.lg data data-driven efficiency inductive knowledge lies low machine machine learning meta meta-learning pipeline prior promote robustness type world