COOKIES: By using this website you agree that we can place Google Analytics Cookies on your device for performance monitoring. |

University of Cambridge > Talks.cam > Isaac Newton Institute Seminar Series > Structured solutions to nonlinear systems of equations

## Structured solutions to nonlinear systems of equationsAdd to your list(s) Download to your calendar using vCal - Justin Romberg (Georgia Institute of Technology)
- Monday 30 October 2017, 17:20-18:10
- Seminar Room 1, Newton Institute.
If you have a question about this talk, please contact info@newton.ac.uk. VMVW02 - Generative models, parameter learning and sparsity 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 non-convex 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. This talk is part of the Isaac Newton Institute Seminar Series series. ## This talk is included in these lists:- All CMS events
- Featured lists
- INI info aggregator
- Isaac Newton Institute Seminar Series
- School of Physical Sciences
- Seminar Room 1, Newton Institute
Note that ex-directory lists are not shown. |
## Other lists80000 Hours Cambridge Philomathia Forum 2017 cambridge immunology## Other talksPeak Youth: the end of the beginning Organoid systems to study the maternal-fetal dialogue of early pregnancy Modulating developmental signals allows establishment of cultures of expanded potential stem cells CGHR Practitioner Series: Andrea Coomber, JUSTICE Foster Talk - Localised RNA-based mechanisms underlie neuronal wiring UK 7T travelling-head study: pilot results |