# A unified framework for high-dimensional analysis of $M$-estimators with decomposable regularizers

@inproceedings{Negahban2009AUF, title={A unified framework for high-dimensional analysis of \$M\$-estimators with decomposable regularizers}, author={Sahand N. Negahban and Pradeep Ravikumar and M. Wainwright and Bin Yu}, booktitle={NIPS}, year={2009} }

High-dimensional statistical inference deals with models in which the the number of parameters p is comparable to or larger than the sample size n. Since it is usually impossible to obtain consistent procedures unless p/n → 0, a line of recent work has studied models with various types of structure (e.g., sparse vectors; block-structured matrices; low-rank matrices; Markov assumptions). In such settings, a general approach to estimation is to solve a regularized convex program (known as a… Expand

#### Supplemental Presentations

Presentation Slides

A unified framework for high-dimensional analysis of $M$-estimators with decomposable regularizers

#### 1,052 Citations

A general framework for high-dimensional estimation in the presence of incoherence

- Mathematics
- 2010 48th Annual Allerton Conference on Communication, Control, and Computing (Allerton)
- 2010

FASt global convergence of gradient methods for solving regularized M-estimation

- Mathematics, Computer Science
- 2012 IEEE Statistical Signal Processing Workshop (SSP)
- 2012

Adaptive Estimation In High-Dimensional Additive Models With Multi-Resolution Group Lasso

- Mathematics
- 2020

Estimation of (near) low-rank matrices with noise and high-dimensional scaling

- Mathematics, Computer Science
- ICML
- 2010

Fast global convergence of gradient methods for high-dimensional statistical recovery

- Mathematics, Computer Science
- ArXiv
- 2011

Fast global convergence rates of gradient methods for high-dimensional statistical recovery

- Computer Science, Mathematics
- NIPS
- 2010

#### References

SHOWING 1-10 OF 137 REFERENCES

Estimation of (near) low-rank matrices with noise and high-dimensional scaling

- Mathematics, Computer Science
- ICML
- 2010

Noisy matrix decomposition via convex relaxation: Optimal rates in high dimensions

- Mathematics, Computer Science
- ICML
- 2011

High-dimensional covariance estimation by minimizing ℓ1-penalized log-determinant divergence

- Mathematics
- 2008

Sparsistency and Rates of Convergence in Large Covariance Matrix Estimation.

- Mathematics, Medicine
- Annals of statistics
- 2009

Restricted Eigenvalue Properties for Correlated Gaussian Designs

- Computer Science, Mathematics
- J. Mach. Learn. Res.
- 2010

Consistency of the group Lasso and multiple kernel learning

- Computer Science, Mathematics
- J. Mach. Learn. Res.
- 2008