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

Despite the considerable progress, it's still a difficult task to realize the real end-to-end training of

In this work, we mainly focus on first-order algorithms, which only need the function value and gradient evaluations.

Extensive experiments on multiple networks show that saddle-points are not the cause for generalization gap of large batch size training, and the results consistently show that large batch converges to points with noticeably higher Hessian spectrum.

Apart from modeling the time to event, in the presence of competing risks, it is also important to model the event type, or under which risk the event is likely to occur first. Though one can censor subjects with an occurrence of the event under a competing risk other than the risk of special interest, so that every survival model that can handle censoring is able to model competing risks, it is problematic to violate the principle of non-informative censoring [18, 19].

The proposed framework is model-agnostic and applicable to any tasks other than VQA, e .

This failure pattern indicates that the learned behavior is better characterized by memorization than by systematic abstraction.

Deep generative models for sequential data are an active field of research.

To facilitate information flow and maintain consistent decoding, we introduce a dual self-attention mechanism that allows us to model complex dependencies between the outputs. We illustrate the performance of our model on the task of video captioning, as well as a synthetic sequence de-noising task.

Optimization is an integral part of most machine learning systems and most numerical optimization schemes rely on the computation of derivatives.