Emmanuel's code





Truncated Wirtinger Flows (TWF)
This implements a novel algorithm for solving certain systems of quadratic equations connected to the famous phase retrieval problem.


Knockoff Filters
This implements the knockoff method, a novel model selection strategy for variable selection which provably controls Type-I errors such as the false discovery rate.


SLOPE: Sorted L-One Penalized Estimation
This provides software for optimizing the sorted L1 norm as in SLOPE. The sorted L1 norm is useful for statistical estimation and testing, particularly for variable selection in the linear model.


SURE for Matrix Estimation
This develops unbiased risk estimates for spectral estimators and applies these formulas for the denoising of real clinical cardiac MRI series data.


Templates for First-Order Conic Solvers (TFOCS, pronounced tee-fox) is a software package that provides a set of templates, or building blocks, that can be used to construct efficient, customized solvers for a variety of models.


NESTA is a fast and robust first-order method that solves minimum l1 problems and a large number of extensions including total-variation minimization. This suite of optimization algorithms is based on ideas from Nesterov, namely, accelerated descent methods and smoothing techniques.


Singular Value Thresholding (SVT)
Singular Value Thresholding (SVT) is an algorithm to minimize the nuclear norm of a matrix, subject to certain types of constraints. It has been successfully used in many matrix-completion problems (for more on the matrix completion problem, see Exact matrix completion via convex optimization by E.J. Candes and B. Recht).


CurveLab is a toolbox implementing the Fast Discrete Curvelet Transform in two and three dimensions, both in Matlab and C++.


L1 MAGIC is a collection of MATLAB routines for solving the convex optimization programs central to compressive sampling. The algorithms are based on standard interior-point methods, and are suitable for large-scale problems.


ChirpLab is a collection of MATLAB routines for the detection of highly oscillatory and nonstationary signals from very noisy data. The methods in ChirpLab might be especially suitable for the detection of gravitational waves in data from laser interferometric detectors such as LIGO.




arrow Home


arrow Publications
arrow Software
arrow Some Talks
arrow Teaching
arrow Students
arrow Analog to Information



arrow Contact Information
arrow EE Home
arrow ICME Home
arrow Mathematics Home
arrow Statistics Home
arrow Stanford Home
arrow C+MS at Caltech




last update: 06/05/2009   ©2007 Caltech. All Rights Reserved.