Gradient-Free Methods for Deterministic and Stochastic Nonsmooth Nonconvex Optimization

Authors: Tianyi Lin, Zeyu Zheng, Michael Jordan

NeurIPS 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Finally, we demonstrate the effectiveness of 2-SGFM on training Re LU neural networks with the MINST dataset.
Researcher Affiliation Academia University of California, Berkeley {darren_lin,zyzheng}@berkeley.edu, jordan@cs.berkeley.edu
Pseudocode Yes Algorithm 1 Gradient-Free Method (GFM)
Open Source Code No The paper includes a checklist at the end stating 'Did you include the code, data, and instructions needed to reproduce the main experimental results (either in the supplemental material or as a URL)? [Yes]', but the main body of the paper does not provide a specific URL or explicit statement about code availability.
Open Datasets Yes The dataset we use is the MNIST dataset1 [60]
Dataset Splits No The paper uses the MNIST dataset but does not explicitly state the training, validation, or test data splits, nor does it refer to predefined splits with citations within the main text.
Hardware Specification Yes All the experiments are implemented using Py Torch [73] on a workstation with a 2.6 GHz Intel Core i7 and 16GB memory.
Software Dependencies No All the experiments are implemented using Py Torch [73] on a workstation with a 2.6 GHz Intel Core i7 and 16GB memory.
Experiment Setup Yes We set the learning rate η as 0.001.