Broken ergodicity and the violation of the fluctuation-dissipation theorem lead to generalization beyond overfitting in machine learning
In the authors' words
This journal does not let us republish the full abstract. Here are the two sentences Pipette selected, quoted from it. Read the rest at the publisher.
Main result
Here we use dynamical mean field theory to show that this so-called "double descent" behavior is the outcome of a phase transition in the stochastic field theory describing the training process.
Appeared: Wednesday, November 4. Physical Review Letters. Peer-reviewed journal.
DOI: 10.1103/bvgf-h18d