Convergence Analysis of Proximal Gradient with Momentum for Nonconvex Optimization

Authors: Qunwei Li, Yi Zhou, Yingbin Liang, Pramod K. Varshney

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

Reproducibility Variable Result LLM Response
Research Type Experimental In this section, we compare the efficiency of APGnc and SVRG-APGnc with other competitive methods via numerical experiments.
Researcher Affiliation Academia 1Syracuse University, NY, USA. Correspondence to: Qunwei Li <qli33@syr.edu>.
Pseudocode Yes Algorithm 1 APG
Open Source Code No The paper does not provide any specific repository links or explicit statements about code availability for the described methodology.
Open Datasets No For the experiment, we set n = 2000, γ = 10^-3 and randomly generate the samples zi from normal distribution. All samples are then normalized to have unit norm. The initialization is randomly generated, and is applied to all the methods. The paper does not provide concrete access information for a publicly available or open dataset.
Dataset Splits No The paper does not provide specific dataset split information (exact percentages, sample counts, or detailed splitting methodology).
Hardware Specification No The paper does not provide specific hardware details (exact GPU/CPU models, processor types, or memory amounts) 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).
Experiment Setup Yes We tuned a fixed step size η = 0.05/L, where L is the spectral norm of the sample matrix n P i=1 ziz T i . We set t = 1/2 for APGnc+. ... and pick the stepsize η = 1/8m L with m = n.