In recent years, transformer-based models have revolutionized deep learning, particularly in sequence modeling.

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

SGD until 100% accuracy is achieved, in four different settings: 1. Random initialization + Training with true labels.

This generalization ability cannot be explained by the capacity of the explicitly specified model class (namely, the functions representable in the chosen architecture). Instead, it seems that the optimization algorithm biases us toward a "simple" model, minimizing

Learning with deep neural networks has enjoyed huge empirical success in recent years across a wide variety of tasks.

Jastrz ebski et al. [6] suggested that the ratio between the learning rate and the batch

The question of which global minima are accessible by a stochastic gradient decent (SGD) algorithm with specific learning rate and batch size is studied from the perspective of dynamical stability. The concept of non-uniformity is introduced, which, together with sharpness, characterizes the stability property of a global minimum and hence the accessibility of a particular SGD algorithm to that global minimum. In particular, this analysis shows that learning rate and batch size play different roles in minima selection. Extensive empirical results seem to correlate well with the theoretical findings and provide further support to these claims.

We study the set of continuous functions that admit no spurious local optima (i.e.