On the Complexity of Low-Rank Matrix Signing and Entrywise Power Matrix Factorization
Nicolas Gillis, Subhayan Saha, Stefano Sicilia, Arnaud Vandaele
cs.CC, cs.IR, math.CO, stat.ML
Submitted: 2026-07-06
Comments: 28 pages, new title and we refined some parts of the paper. code available from https://gitlab.com/ngillis/rank-r_signing/
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Alternating Direction Method of Multipliers for Nonlinear Matrix Decompositions
- The complexity of computing the minimum rank of a sign pattern matrix
- An extrapolated and provably convergent algorithm for nonlinear matrix decomposition with the ReLU function
- Manifold-based Algorithms for the Hadamard Decomposition
- Binary component decomposition Part II: The asymmetric case
- The square root rank of the correlation polytope is exponential
Related papers
- Parameterized Hardness of Zonotope Containment and Neural Network Verification
- Optimal Unambiguous DNFs and Alon-Saks-Seymour
- On the Limits of Quantum Multiparty Simultaneous Communication
- Learning, Compression, and Meta-Complexity
- Hardware-Algorithm Co-Optimization of Early-Exit Neural Networks for Multi-Core Edge Accelerators
- Quantum Fine-Grained Lower Bounds for SetDisjointness via Sub-Linear Reductions from 3SUM