But how to explain this phenomenon has been largely ignored by existing studies.

Neural Information Processing Systems http://nips.cc/

We theoretically study the landscape of the training error for neural networks in overparameterized cases.

Our first algorithm consists of a simple modification of the ML model used by Lewis et al. and applies to a property of interest known in advance.

This important phenomenon commonly appears in implemented neural network architectures, and also seems to emerge in epoch-wise curves during the training process.

Ensembling has a long history in statistical data analysis, with many impactful applications. However, in many modern machine learning settings, the benefits of ensembling are less ubiquitous and less obvious.