A Nonconvex Optimization Framework for Low Rank Matrix Estimation

Authors: Tuo Zhao, Zhaoran Wang, Han Liu

NeurIPS 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We present numerical experiments for matrix sensing to support our theoretical analysis. We choose m = 30, n = 40, and k = 5, and vary d from 300 to 900. Each entry of Ai s are independent sampled from N(0, 1). We then generate M = UV >, where e U 2 Rm k and e V 2 Rn k are two matrices with all their entries independently sampled from N(0, 1/k). We then generate d measurements by bi = h Ai, Mi for i = 1, ..., d. Figure 1 illustrates the empirical performance of the alternating exact minimization and alternating gradient descent algorithms for a single realization.
Researcher Affiliation Academia Tuo Zhao Johns Hopkins University Zhaoran Wang Han Liu Princeton University
Pseudocode Yes Algorithm 1 A family of nonconvex optimization algorithms for matrix sensing.
Open Source Code No The paper does not provide any links or explicit statements about the availability of open-source code for the described methodology.
Open Datasets No The paper describes generating synthetic data for experiments ('Each entry of Ai s are independent sampled from N(0, 1). We then generate M = UV >'), but it does not use or provide access to a publicly available or open dataset.
Dataset Splits No The paper describes generating data for its experiments but does not specify any training, validation, or test dataset splits, percentages, or a methodology for creating such splits.
Hardware Specification No The paper does not provide any specific details about the hardware (e.g., GPU/CPU models, memory) used to run the experiments.
Software Dependencies No The paper does not provide specific software dependencies, libraries, or solvers with version numbers.
Experiment Setup Yes The step size for the alternating gradient descent algorithm is determined by the backtracking line search procedure.