Primal-Dual Block Generalized Frank-Wolfe

Authors: Qi Lei, JIACHENG ZHUO, Constantine Caramanis, Inderjit S. Dhillon, Alexandros G. Dimakis

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

Reproducibility Variable Result LLM Response
Research Type Experimental We empirically show that our algorithm outperforms the state-of-the-art methods on (multi-class) classification tasks.
Researcher Affiliation Collaboration UT Austin Amazon {leiqi@oden., jzhuo@, constantine@, inderjit@cs., dimakis@austin.}utexas.edu
Pseudocode Yes Algorithm 1 Primal-Dual Block Generalized Frank-Wolfe Method for ℓ1 Norm Ball
Open Source Code Yes The codes to reproduce our results could be found in https://github.com/Carlson Zhuo/ primal_dual_frank_wolfe.
Open Datasets Yes The six datasets used here are summarized in Table 2. All of them can be found in LIBSVM datasets [4].
Dataset Splits No The paper does not provide specific dataset split information (exact percentages, sample counts, citations to predefined splits, or detailed splitting methodology) needed to reproduce the data partitioning.
Hardware Specification No The paper does not provide specific hardware details (exact GPU/CPU models, processor types with speeds, memory amounts, or detailed computer specifications) used for running its experiments.
Software Dependencies Yes Algorithms are implemented in C++, with the Eigen linear algebra library [12].
Experiment Setup Yes We set the ℓ1 constraint to be 300 and the ℓ2 regularize parameter to 10/n to achieve reasonable prediction accuracy.