Multi-view Matrix Factorization for Linear Dynamical System Estimation
Authors: Mahdi Karami, Martha White, Dale Schuurmans, Csaba Szepesvari
NeurIPS 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We evaluate the proposed algorithm by comparing one step prediction performance and computation speed with alternative methods for real and synthetic time series. ... The NMSE and run-time results obtained on real and synthetic datasets are shown in Table 1 and Table 2, respectively. |
| Researcher Affiliation | Academia | Department of Computer Science University of Alberta Edmonton, AB, Canada {karami1, whitem, daes, szepesva}@ualberta.ca |
| Pseudocode | Yes | Algorithm 1 LDS-DV |
| Open Source Code | No | The paper does not include any explicit statement about releasing source code for the described methodology or a direct link to a code repository. |
| Open Datasets | No | The paper mentions 'climate time series from IRI data library', 'tropical Atlantic ocean (ATL) and tropical Pacific ocean (CAC)', and synthetic datasets. However, it does not provide concrete access information (link, DOI, specific repository, or formal citation with authors/year for public datasets) for these datasets. |
| Dataset Splits | No | The paper mentions '70% training and 30% test' splits for real and synthetic data, but does not explicitly mention or quantify a separate validation set split. |
| Hardware Specification | No | The paper does not provide any specific hardware details (e.g., GPU/CPU models, memory) used for running its experiments. It only mentions 'runtime in CPU seconds' but no CPU model. |
| Software Dependencies | No | The paper mentions 'Matlab' functions 'n4sid' and 'pem', but does not provide version numbers for Matlab or any other software dependencies. |
| Experiment Setup | Yes | The estimated parameters by N4SID were used as the initialization point for EM and PEM algorithms in our experiments. We used the built-in functions, n4sid and pem, in Matlab, with the order selected by the function... For our algorithm, we select the regularization parameter λ using cross-validation. |