Efficient Inexact Proximal Gradient Algorithm for Nonconvex Problems

Authors: Quanming Yao, James T. Kwok, Fei Gao, Wei Chen, Tie-Yan Liu

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

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments on a number of problems demonstrate that the proposed algorithm has comparable performance as the state-of-the-art, but is much faster.In this section, we perform experiments when g is convex (Section 5.1) and nonconvex (Section 5.2).
Researcher Affiliation Collaboration Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong1 Microsoft Research, Beijing, China2
Pseudocode Yes Algorithm 1 Nonmonotone APG (nm APG). Algorithm 2 Noconvex inexact APG (ni APG) algorithm.
Open Source Code No The paper does not provide any explicit statement or link indicating that the source code for the described methodology is open-source or publicly available.
Open Datasets Yes Experiments are performed on the Lena image. Movie Lens data sets (Table 6), which contain ratings of different users on movies or musics. Finally, we perform experiments on the large Netflix and Yahoo data sets (Table 6).
Dataset Splits Yes Half of them [observed entries in synthetic data] are used for training, and the rest as validation set. we use 50% of the observed ratings for training, 25% for validation and the rest for testing.
Hardware Specification No The paper mentions 'CPU time' in its results tables but does not provide any specific hardware details such as CPU or GPU models, memory, or cloud instance types used for the experiments.
Software Dependencies No The paper mentions algorithms like L-BFGS, power method, and Lancoz algorithm, but does not provide specific version numbers for any software libraries, frameworks, or programming languages used in the implementation of their method or experiments.
Experiment Setup Yes In the experiments, q is set to 5 as in [Wright et al., 2009; Gong et al., 2013]. inexactness of the proximal step is controlled by decaying the duality gap εk at a rate of O(1/k1.5) and rank is tuned by the validation set.