The Loss Surface of Deep and Wide Neural Networks

Authors: Quynh Nguyen, Matthias Hein

ICML 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We show that this is (almost) true, in fact almost all local minima are globally optimal, for a fully connected network with squared loss and analytic activation function given that the number of hidden units of one layer of the network is larger than the number of training points and the network structure from this layer on is pyramidal.
Researcher Affiliation Academia Quynh Nguyen 1 Matthias Hein 1 1Department of Mathematics and Computer Science, Saarland University, Germany. Correspondence to: Quynh Nguyen <quynh@cs.uni-saarland.de>.
Pseudocode No The paper does not contain any pseudocode or clearly labeled algorithm blocks.
Open Source Code No The paper does not provide any statement or link regarding the release of source code for the described methodology.
Open Datasets No The paper is theoretical and does not describe experiments on a specific, publicly available dataset with concrete access information.
Dataset Splits No This is a theoretical paper and does not describe experiments that would involve dataset splits.
Hardware Specification No The paper does not describe any experiments, and therefore no specific hardware specifications are mentioned.
Software Dependencies No The paper is theoretical and does not mention any specific software dependencies with version numbers for reproducing experiments.
Experiment Setup No The paper is theoretical and does not provide details about an experimental setup, such as hyperparameters or system-level training settings.