Abstract | ||
---|---|---|
•Matrix completion under interval uncertainty can be encoded using box constraints.•E.g. in collaborative filtering, a rating of 2 can be replaced by an interval 1–3.•Present-best results in terms of statistical performance are provided for a benchmark.•Convergence of randomized coordinate-descent methods to stationary points is proven. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1016/j.ejor.2016.07.014 | European Journal of Operational Research |
Keywords | Field | DocType |
Matrix completion,Robust optimization,Collaborative filtering,Coordinate descent,Large-scale optimization | Mathematical optimization,Collaborative filtering,Matrix completion,Robust optimization,Personal computer,Coordinate descent,Mathematics | Journal |
Volume | Issue | ISSN |
256 | 1 | 0377-2217 |
Citations | PageRank | References |
4 | 0.41 | 36 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jakub Marecek | 1 | 134 | 15.10 |
Peter Richtárik | 2 | 1314 | 84.53 |
Martin Takác | 3 | 752 | 49.49 |