paper-with-me

Papers

Depth with Nonlinearity Creates No Bad Local Minima in ResNets

2018-10-21 · Kenji Kawaguchi, Yoshua Bengio

In this paper, we prove that depth with nonlinearity creates no bad local minima in a type of arbitrarily deep ResNets with arbitrary nonlinear activation functions, in the sense that the values of all local minima are no worse than the global minimum value of corresponding classical machine-learning models, and are guaranteed to further improve via residual representations. As a result, this paper provides an affirmative answer to an open question stated in a paper in the conference on Neural Information Processing Systems 2018. This paper advances the optimization theory of deep learning only for ResNets and not for other network architectures.

📄 PDF Abstract BibTeX arXiv:1810.09038

Code (0)

등록된 구현이 없습니다.

Tasks

BIG-bench Machine LearningOpen-Ended Question Answering

Similar Papers 제목 키워드 기반

Depth Creates No Bad Local Minima

2017-02-27 · Haihao Lu, Kenji Kawaguchi

In deep learning, \textit{depth}, as well as \textit{nonlinearity}, create non-convex loss surfaces. Then, does depth alone create bad local minima? In this paper, we prove that without nonlinearity, depth alone does not…

Are deep ResNets provably better than linear predictors?

2019-07-09 · NeurIPS 2019 12 · Chulhee Yun, Suvrit Sra, Ali Jadbabaie

Recent results in the literature indicate that a residual network (ResNet) composed of a single residual block outperforms linear predictors, in the sense that all local minima in its optimization landscape are at least …

Are All Linear Regions Created Equal?

2022-02-23 · Matteo Gamba, Adrian Chmielewski-Anders, Josephine Sullivan, Hossein Azizpour 외

The number of linear regions has been studied as a proxy of complexity for ReLU networks. However, the empirical success of network compression techniques like pruning and knowledge distillation, suggest that in the over…

AllKnowledge Distillation

Depth creates no more spurious local minima

2019-01-28 · Li Zhang

We show that for any convex differentiable loss, a deep linear network has no spurious local minima as long as it is true for the two layer case. This reduction greatly simplifies the study on the existence of spurious l…

Depth creates no more spurious local minima in linear networks

2019-09-25 · Li Zhang

We show that for any convex differentiable loss, a deep linear network has no spurious local minima as long as it is true for the two layer case. This reduction greatly simplifies the study on the existence of spurious…