Deep Linear Networks with Arbitrary Loss: All Local Minima Are Global
Authors: Thomas Laurent, James Brecht
ICML 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | We provide a short and elementary proof of the fact that all local minima are global minima if the hidden layers are either 1) at least as wide as the input layer, or 2) at least as wide as the output layer. |
| Researcher Affiliation | Academia | 1Department of Mathematics, Loyola Marymount University, Los Angeles, CA 90045, USA 2Department of Mathematics and Statistics, California State University, Long Beach, Long Beach, CA 90840, USA. |
| Pseudocode | No | The paper is purely theoretical, focusing on mathematical proofs and theorems. It does not contain any pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not mention or provide any links to open-source code for the methodology described. |
| Open Datasets | No | The paper is a theoretical work focusing on mathematical proofs regarding deep linear networks. It does not involve any experimental training on datasets, public or otherwise. |
| Dataset Splits | No | The paper is theoretical and does not describe any experimental setup involving dataset splits for training, validation, or testing. |
| Hardware Specification | No | The paper is theoretical and does not describe any experiments that would require specific hardware. Therefore, no hardware specifications are mentioned. |
| Software Dependencies | No | The paper is theoretical and does not involve practical implementations or experiments, thus no software dependencies with version numbers are mentioned. |
| Experiment Setup | No | The paper is a theoretical work providing proofs and analysis of deep linear networks. It does not include details about an experimental setup, such as hyperparameters or training configurations. |