On the Global Linear Convergence of Frank-Wolfe Optimization Variants

Authors: Simon Lacoste-Julien, Martin Jaggi

NeurIPS 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We illustrate the performance of the presented algorithm variants in two numerical experiments, shown in Figure 2.
Researcher Affiliation Academia Simon Lacoste-Julien INRIA SIERRA project-team Ecole Normale Sup erieure, Paris, France Martin Jaggi Dept. of Computer Science ETH Z urich, Switzerland
Pseudocode Yes Algorithm 1 Away-steps Frank-Wolfe algorithm: AFW(x(0), A, ϵ)
Open Source Code No Code is available from the authors website.
Open Datasets Yes For the LMOA, we re-use the code provided by [16] and their included aeroplane dataset resulting in a QP over 660 variables.
Dataset Splits No Not found. The paper does not specify exact train/validation/test split percentages, sample counts, or cross-validation setup for the datasets used.
Hardware Specification No Not found. The paper does not provide specific hardware details (e.g., GPU/CPU models, memory, or cloud resources) used for the experiments.
Software Dependencies No Not found. The paper does not list specific software dependencies with version numbers (e.g., Python 3.8, PyTorch 1.9, CPLEX 12.4).
Experiment Setup No Not found. The paper does not provide specific experimental setup details such as hyperparameter values (e.g., learning rate, batch size) or explicit training configurations.