no code implementations • 15 Feb 2022 • Dominic Belcher, Antonia Marcu, Adam Prügel-Bennett
In this paper we show that the expected generalisation performance of a learning machine is determined by the distribution of risks or equivalently its logarithm -- a quantity we term the risk entropy -- and the fluctuations in a quantity we call the training ratio.
no code implementations • NeurIPS Workshop DL-IG 2020 • Dominic Belcher, Adam Prugel-Bennett, Srinandan Dasmahapatra
Recent results in deep learning show that considering only the capacity of machines does not adequately explain the generalisation performance we can observe.
