Exploiting Strong Convexity from Data with Primal-Dual First-Order Algorithms

Authors: Jialei Wang, Lin Xiao

ICML 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental 5. Preliminary experiments We present preliminary experiments to demonstrate the effectiveness of our proposed algorithms. First, we consider batch primal-dual algorithms for ridge regression over a synthetic dataset.
Researcher Affiliation Collaboration 1Department of Computer Science, The University of Chicago, Chicago, Illinois 60637, USA. 2Microsoft Research, Redmond, Washington 98052, USA.
Pseudocode Yes Algorithm 1 Batch Primal-Dual (BPD) Algorithm
Open Source Code No The paper does not provide any explicit statements about releasing source code for the described methodology or include any links to code repositories.
Open Datasets Yes cpuact data from the Lib SVM website (https://www.csie.ntu.edu.tw/ cjlin/libsvm/)
Dataset Splits No The paper mentions using synthetic and real-world datasets (cpuact, rcv1) but does not provide specific details on how these datasets were split into training, validation, and test sets for the experiments.
Hardware Specification No The paper discusses algorithmic performance and experimental results but does not provide specific hardware details (e.g., CPU, GPU models, memory) used for running the experiments.
Software Dependencies No The paper mentions names of algorithms and data sources (e.g., Lib SVM website) but does not provide specific software dependencies with version numbers (e.g., programming languages, libraries, frameworks with their versions) that would be needed to replicate the experiments.
Experiment Setup Yes The step sizes of all algorithms are set as their original paper suggested. For Ada-SPDC and ADF-SPDC, we use the robust adaptation scheme with T = 10, c = 0.95 and c = 1.5. For SVRG and Katyusha (an accelerated variant of SVRG), we choose the variance reduction period as m = 2n.