Symmetry constrained machine learning
This addresses over-fitting issues for machine learning practitioners, though it is incremental as it applies known symmetry concepts to ML.
The paper tackles the problem of over-fitting in machine learning by incorporating symmetries into models, demonstrating that this approach reduces over-fitting, lowers complexity, and requires less training data and resources, as shown with a neural network for handwritten digit classification.
Symmetry, a central concept in understanding the laws of nature, has been used for centuries in physics, mathematics, and chemistry, to help make mathematical models tractable. Yet, despite its power, symmetry has not been used extensively in machine learning, until rather recently. In this article we show a general way to incorporate symmetries into machine learning models. We demonstrate this with a detailed analysis on a rather simple real world machine learning system - a neural network for classifying handwritten digits, lacking bias terms for every neuron. We demonstrate that ignoring symmetries can have dire over-fitting consequences, and that incorporating symmetry into the model reduces over-fitting, while at the same time reducing complexity, ultimately requiring less training data, and taking less time and resources to train.