The most forceful driver of advancements in the field of Machine Learning over the past decades has been the success of deep neural networks.

In this work, we provide a comparative analysis of the learning dynamics for the Euclidean and cosine-based asymmetric losses in the eigenspace of the closed-form predictor DirectPred.

Unfortunately, even for standard linear networks in regression setting, a comprehensive characterization of the implicit bias is still an open problem.

The largest eigenvalue of the Hessian, or sharpness, of neural networks is a key quantity to understand their optimization dynamics.

Deep neural networks have significantly advanced machine learning in recent decades.

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