On the optimization landscape of tensor decompositions
From MaRDI portal
Publication:2144549
DOI10.1007/s10107-020-01579-xzbMath1494.90085arXiv1706.05598OpenAlexW3094331929MaRDI QIDQ2144549
Publication date: 14 June 2022
Published in: Mathematical Programming. Series A. Series B (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1706.05598
Related Items (2)
Analysis of the optimization landscape of Linear Quadratic Gaussian (LQG) control ⋮ Notes on computational-to-statistical gaps: predictions using statistical physics
Cites Work
- Unnamed Item
- Unnamed Item
- A spectral algorithm for learning hidden Markov models
- Probability in Banach spaces. Isoperimetry and processes
- A tail inequality for quadratic forms of subgaussian random vectors
- The restricted isometry property and its implications for compressed sensing
- A simple proof of the restricted isometry property for random matrices
- Full reconstruction of Markov models on evolutionary trees: identifiability and consistency.
- Adaptive estimation of a quadratic functional by model selection.
- The number of eigenvalues of a tensor
- A spectral algorithm for latent Dirichlet allocation
- Complexity of random smooth functions on the high-dimensional sphere
- Cubic regularization of Newton method and its global performance
- Dictionary Learning and Tensor Decomposition via the Sum-of-Squares Method
- Eigenconfigurations of tensors
- Learning mixtures of spherical gaussians
- Non-asymptotic theory of random matrices: extreme singular values
- Tensor rank is NP-complete
- Shifted Power Method for Computing Tensor Eigenpairs
- Decoding by Linear Programming
- Gradient Descent Learns Linear Dynamical Systems
- Fourth-Order Cumulant-Based Blind Identification of Underdetermined Mixtures
- Random Matrices and Complexity of Spin Glasses
- Global rates of convergence for nonconvex optimization on manifolds
- Fourier PCA and robust tensor decomposition
- Smoothed analysis of tensor decompositions
- Random Fields and Geometry
- Decomposing Overcomplete 3rd Order Tensors using Sum-of-Squares Algorithms
- Fast spectral algorithms from sum-of-squares proofs: tensor decomposition and planted sparse vectors
- Most Tensor Problems Are NP-Hard
- Learning nonsingular phylogenies and hidden Markov models
This page was built for publication: On the optimization landscape of tensor decompositions
