Fine-grained Optimization of Deep Neural Networks

Authors: Mete Ozay

NeurIPS 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental analyses show that image classification accuracy of baseline DNNs can be boosted using FG-SGD on collections of manifolds identified by multiple constraints. Due to page limit, experimental analyses are given in the supplemental material. In these analyses, we observe that our proposed methods can improve convergence properties and classification performance of CNNs.
Researcher Affiliation Academia meteozay@gmail.com. The paper provides a personal email address but lacks clear institutional names (university or company) to definitively classify the author's affiliation type. Given the conference (NeurIPS), it is likely academic, but explicit institutional names are not present.
Pseudocode Yes Algorithm 1 Optimization using FG-SGD on products manifolds of fine-grained weights.
Open Source Code No The paper does not provide any statement about releasing source code, nor does it include a link to a code repository.
Open Datasets No The paper refers to "various datasets" and mentions ImageNet in the references, but it does not explicitly state which datasets were used for its experiments within the main text or provide concrete access information (link, DOI, formal citation in context) for any public dataset it utilized.
Dataset Splits No The paper mentions "training set" and states "Implementation details and experimental analyses are given in the supp. mat.", but it does not provide specific details on training, validation, or test dataset splits (e.g., percentages, sample counts) in the main text.
Hardware Specification No The paper does not provide any specific details about the hardware (e.g., GPU models, CPU types) used for running the experiments.
Software Dependencies No The paper does not list any specific software dependencies with version numbers (e.g., programming languages, libraries, frameworks) that would be needed to reproduce the experiments.
Experiment Setup No The paper mentions "Θ (set of hyperparameters)" as an input to its algorithm but does not provide specific values for these hyperparameters or other concrete details about the experimental setup or training configurations in the main text.