Non-asymptotic Analysis of Stochastic Methods for Non-Smooth Non-Convex Regularized Problems

Authors: Yi Xu, Rong Jin, Tianbao Yang

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

Reproducibility Variable Result LLM Response
Research Type Experimental 5 Experiments Regularized loss minimization. First, we compare MB-SPG, SPGR with MBSGA, VRSGA, SSDC-SPG and SSDC-SVRG for solving the regularized non-linear least square (NLLS) classification problems [...] Two data sets (covtype and a9a) are used for classification, and two data sets E2006 and triazines are used for regression.
Researcher Affiliation Collaboration Yi Xu1, Rong Jin2, Tianbao Yang1 1. Department of Computer Science, The University of Iowa, Iowa City, IA 52246, USA 2. Machine Intelligence Technology, Alibaba Group, Bellevue, WA 98004, USA
Pseudocode Yes Algorithm 1 Mini-Batch Stochastic Proximal Gradient: MB-SPG
Open Source Code No The paper does not provide concrete access to source code (specific repository link, explicit code release statement, or code in supplementary materials) for the methodology described in this paper.
Open Datasets Yes Two data sets (covtype and a9a) are used for classification, and two data sets E2006 and triazines are used for regression. These data sets are downloaded from the libsvm website.
Dataset Splits No The paper mentions using well-known datasets but does not explicitly specify the exact train/validation/test splits (e.g., percentages, absolute counts, or cross-validation scheme) used for experiments.
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 No The paper does not provide specific ancillary software details (e.g., library or solver names with version numbers like Python 3.8, CPLEX 12.4) needed to replicate the experiment.
Experiment Setup Yes The truncation value α is set to 10n following [44]. The value of regularization parameter λ is fixed as 10 4 and the value of κ is fixed as 0.2d where d is the dimension of data. For all algorithms, we use the theoretical values of the parameters for the sake of fairness in comparison. All algorithms start with the same initial solution with all zero entries. We implement the increasing mini-batch versions of MB-SPG and SPGR (online setting) with b = 1.