Random matrix methods for machine learning
From MaRDI portal
Recommendations
- A first course in random matrix theory: for physicists, engineers and data scientists
- High-dimensional covariance matrix estimation. An introduction to random matrix theory
- Mathematical theories of machine learning: theory and applications
- Random Matrices: High Dimensional Phenomena
- Spectral analysis of large dimensional random matrices
Cited in
(17)- Enhancing accuracy in deep learning using random matrix theory
- Linear eigenvalue statistics of XX′ matrices
- A random matrix approach to low-multilinear-rank tensor approximation
- A spectral approach to Hebbian-like neural networks
- Entropy dimension reduction method for randomized machine learning problems
- Structured random matrices and cyclic cumulants: a free probability approach
- High-dimensional non-convex landscapes and gradient descent dynamics
- Large-dimensional random matrix theory and its applications in deep learning and wireless communications
- The Kaczmarz algorithm, row action methods, and statistical learning algorithms
- Dyson equation for correlated linearizations and test error of random features regression
- Spectra of large dimensional random Gram matrices under partial dependence
- Robust two-way dimension reduction by Grassmannian barycenter
- A first course in random matrix theory: for physicists, engineers and data scientists
- Homogenization of SGD in high-dimensions: exact dynamics and generalization properties
- Free dynamics of feature learning processes
- Randomized machine learning procedures
- A consistent estimator for confounding strength
This page was built for publication: Random matrix methods for machine learning
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5086565)
