High-Dimensional Probability: An Introduction with Applications in Data Science

@inproceedings{Vershynin2018HighDimensionalPA,
  title={High-Dimensional Probability: An Introduction with Applications in Data Science},
  author={R. Vershynin},
  year={2018}
}
High-dimensional probability offers insight into the behavior of random vectors, random matrices, random subspaces, and objects used to quantify uncertainty in high dimensions. Drawing on ideas from probability, analysis, and geometry, it lends itself to applications in mathematics, statistics, theoretical computer science, signal processing, optimization, and more. It is the first to integrate theory, key tools, and modern applications of high-dimensional probability. Concentration… Expand
Dimension-Free Error Bounds from Random Projections
Four lectures on probabilistic methods for data science
High-Dimensional Optimization in Adaptive Random Subspaces
Random Quadratic Forms with Dependence: Applications to Restricted Isometry and Beyond
Comparing a Large Number of Multivariate Distributions
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 214 REFERENCES
Universality laws for randomized dimension reduction, with applications
Living on the edge: phase transitions in convex programs with random data
Introduction to the non-asymptotic analysis of random matrices
  • R. Vershynin
  • Mathematics, Computer Science
  • Compressed Sensing
  • 2012
Lectures on discrete geometry
  • J. Matousek
  • Computer Science, Mathematics
  • Graduate texts in mathematics
  • 2002
Isotropically random orthogonal matrices: Performance of LASSO and minimum conic singular values
The Convex Geometry of Linear Inverse Problems
Matrix analysis
...
1
2
3
4
5
...