Cross-Learning from Scarce Data via Multi-Task Constrained Optimization

doi:10.1109/tsp.2026.3720302

Cross-Learning from Scarce Data via Multi-Task Constrained Optimization

2026-08-03

0

PRE

AI

DOI：10.1109/tsp.2026.3720302

Original

Original request for help

Save

Abstract

En 中文

A learning task, understood as the problem of fitting a parametric model from supervised data, fundamentally requires the dataset to be large enough to be representative of the underlying distribution of the source. When data is limited, the learned models fail generalize to cases not seen during training. This paper introduces a multi-task <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">cross-learning</i> framework to overcome data scarcity by jointly estimating <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">deterministic</i> parameters across multiple, related tasks. We formulate this joint estimation as a constrained optimization problem, where the constraints dictate the resulting similarity between the parameters of the different models, allowing the estimated parameters to differ across tasks while still combining information from multiple data sources. This framework enables knowledge transfer from tasks with abundant data to those with scarce data, leading to more accurate and reliable parameter estimates, providing a solution for scenarios where parameter inference from limited data is critical. We provide theoretical guarantees in a controlled framework with Gaussian data, and show the efficiency of our cross-learning method in applications with real data including image classification and propagation of infectious diseases.

Keywords:

Supervised learning

multi-task

optimization

Cross-Learning from Scarce Data via Multi-Task Constrained Optimization

Abstract

Journal

Organization