3
Structured solutions to nonlinear systems of equations
http://sms.cam.ac.uk/media/2596873
Romberg, J
Monday 30th October 2017  17:20 to 18:10
40
Structured solutions to nonlinear systems of equations
http://sms.cam.ac.uk/media/2596873
http://rss.sms.cam.ac.uk/itunesimage/2555224.jpg
no

Structured solutions to nonlinear systems of equations
ucs_sms_2555223_2596873
http://sms.cam.ac.uk/media/2596873
Structured solutions to nonlinear systems of equations
Romberg, J
Monday 30th October 2017  17:20 to 18:10
Tue, 31 Oct 2017 14:13:43 +0000
Isaac Newton Institute
Romberg, J
98a5585fd654fbe04431f6c8f22b1986
0c6bac3a8b5c1f14dbd79ec9b2419e37
c6ce0b0252a7f67d30b50d3f73bed14c
833d18b90a117ccca3120c60208a9565
Romberg, J
Monday 30th October 2017  17:20 to 18:10
Romberg, J
Monday 30th October 2017  17:20 to 18:10
Cambridge University
2784
http://sms.cam.ac.uk/media/2596873
Structured solutions to nonlinear systems of equations
Romberg, J
Monday 30th October 2017  17:20 to 18:10
We consider the question of estimating a solution to a system of equations that involve convex nonlinearities, a problem that is common in machine learning and signal processing. Because of these nonlinearities, conventional estimators based on empirical risk minimization generally involve solving a nonconvex optimization program. We propose a method (called "anchored regression”) that is based on convex programming and amounts to maximizing a linear functional (perhaps augmented by a regularizer) over a convex set. The proposed convex program is formulated in the natural space of the problem, and avoids the introduction of auxiliary variables, making it computationally favorable. Working in the native space also provides us with the flexibility to incorporate structural priors (e.g., sparsity) on the solution. For our analysis, we model the equations as being drawn from a fixed set according to a probability law. Our main results provide guarantees on the accuracy of the estimator in terms of the number of equations weare solving, the amount of noise present, a measure of statistical complexity of the random equations, and thegeometry of the regularizer at the true solution. We also provide recipes for constructing the anchor vector (that determines the linear functional to maximize) directly from the observed data. We will discuss applications of this technique to nonlinear problems including phase retrieval, blind deconvolution, and inverting the action of a neural network. This is joint work with Sohail Bahmani.
20171031T14:13:43+00:00
2784
2596873
true
16x9
false
no