#### The Mathematics of Data Group Meetings (MDGM) are held every Wednesday,* 2pm at the Center for Data Science (NYU, #60, 5th Ave, Room 606)*

The Group broad interest lies in *big data, convex optimization, signal processing and machine learning*. A particular emphasis is put on developing new inovative approaches enabling the estimation of parameters or recovery of data from a limited amount of information.

### Schedule:

Thursday 12/15 | Ronen Eldan, Weizmann |

Wednesday 01/25 | Jon Weed, MIT |

Wednesday 02/08 | Martin Arjovsky, CIMS |

### Papers of interest (reading list)

- Convexified Convolutional Neural Networks
- PhaseMax: Convex Phase Retrieval via Basis Pursuit
- The Nonconvex Geometry of Low-Rank Matrix Optimizations with General Objective Functions
- Global Convergence of Stochastic Gradient Descent for Some Nonconvex Matrix Problems
- ShapeFit: Exact location recovery from corrupted pairwise directions
- A geometric analysis of phase retrieval
- Understanding deep learning requires rethinking generalization
- Statistical Physics of inference