Sharp bounds for multiple models in matrix completion
From MaRDI portal
Cites work
- A shrinkage principle for heavy-tailed data: high-dimensional robust low-rank matrix recovery
- A simpler approach to matrix completion
- Concentration inequalities for polynomials in \(\alpha\)-sub-exponential random variables
- Dynamic Matrix Recovery
- High-dimensional probability. An introduction with applications in data science
- High-dimensional statistics. A non-asymptotic viewpoint
- I-LAMM for sparse learning: simultaneous control of algorithmic complexity and statistical error
- Low-rank matrix recovery under heavy-tailed errors
- Matrix concentration inequalities and free probability
- Noisy low-rank matrix completion with general sampling distribution
- Noisy matrix completion: understanding statistical guarantees for convex relaxation via nonconvex optimization
- Nuclear-norm penalization and optimal rates for noisy low-rank matrix completion
- Restricted strong convexity and weighted matrix completion: optimal bounds with noise
- Robust low-rank matrix estimation
- Robust matrix completion
- Sub-Gaussian estimators of the mean of a random matrix with heavy-tailed entries
- Tail bounds via generic chaining
- The Power of Convex Relaxation: Near-Optimal Matrix Completion
- User-friendly tail bounds for sums of random matrices
This page was built for publication: Sharp bounds for multiple models in matrix completion
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7235704)
