Homotopy Smoothing for Non-Smooth Problems with Lower Complexity than $O(1/\epsilon)$

Authors: Yi Xu, Yan Yan, Qihang Lin, Tianbao Yang

NeurIPS 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results verify the effectiveness of HOPS in comparison with Nesterov s smoothing algorithm and the primal-dual style of first-order methods.
Researcher Affiliation Academia Department of Computer Science, University of Iowa, Iowa City, IA 52242 QCIS, University of Technology Sydney, NSW 2007, Australia Department of Management Sciences, University of Iowa, Iowa City, IA 52242
Pseudocode Yes Algorithm 1 An Accelerated Proximal Gradient Method: APG(x0, t, Lµ) and Algorithm 2 HOPS for solving (1)
Open Source Code No The paper does not provide an explicit statement about releasing source code for the described methodology or a link to a code repository.
Open Datasets Yes We conduct experiments for solving three problems: (1) an ℓ1-norm regularized hinge loss for linear classification on the w1a dataset 6; (2) a total variation based ROF model for image denoising on the Cameraman picture 7; (3) a nuclear norm regularized absolute error minimization for low-rank and sparse matrix decomposition on a synthetic data. Footnote 6 points to "https://www.csie.ntu.edu.tw/~cjlin/libsvmtools/datasets/" and footnote 7 points to "http://pages.cs.wisc.edu/~swright/TVdenoising/".
Dataset Splits No The paper mentions using specific datasets but does not provide explicit details about training, validation, and test splits (e.g., percentages or sample counts).
Hardware Specification No The paper does not provide specific details about the hardware used for running the experiments (e.g., GPU/CPU models, memory specifications).
Software Dependencies No The paper does not list specific software dependencies with version numbers (e.g., Python 3.x, PyTorch 1.x, specific solver versions).
Experiment Setup No The paper states: "More details about the formulations and experimental setup can be found in the supplement." This indicates that the specific experimental setup details are not present in the main text.