The 2019 MINDS Symposium on the Foundations of Data Science will be held November 20, 2019 in Shriver Hall.

Leading data science researchers will discuss the importance of data science in their fields and the continued need for advancement.

Register for the 2019 MINDS Symposium

Having trouble registering? Click here to register directly on Eventbrite.

Confirmed Speakers

Raman Arora Johns Hopkins University	Sanjeev Arora Princeton University	Joan Bruna New York University
Arnaud Doucet University of Oxford / DeepMind	Anna Gilbert University of Michigan	Charles Meneveau Johns Hopkins University
Amit Singer Princeton University	Jeremias Sulam Johns Hopkins University	Archana Venkataraman Johns Hopkins University
Martin Wainwright University of California at Berkeley	Rachel Ward UT Austin

---

Agenda

Time	Speaker	Affiliation	Title of Presentation
Opening Ceremony
9:00	Ed Schlesinger	Benjamin T. Rome Dean, Whiting School of Engineering, Johns Hopkins University	Introductory Remarks
9:10	René Vidal	Herschel Seder Professor of Biomedical Engineering, Director of the Mathematical Institute for Data Science, Johns Hopkins University	Annoucement of TRIPODS & Awards Ceremony
Session 1
9:30	Sanjeev Arora	Charles C. Fitzmorris Professor of Computer Science, Princeton University	Is optimization the right language to understand deep learning?
10:00	Raman Arora	Assistant Professor of Computer Science, Johns Hopkins University	Online Learning in Reactive Environments
10:15	Lin Yang	Assistant Professor of Electrical & Computer Engineering, UCLA	Taming big data by streaming
10:30	Coffee Break
Session 2
11:00	Martin Wainwright	Chancellor's Professor of Statistics, Electrical Engineering and Computer Sciences, UC Berkeley	From Optimization to Statistical Learning: A View from the Interface
11:30	Arnaud Doucet	Professor of Statistics, University of Oxford & Research Scientist, DeepMind	Exact Simulation for State-Space Models
12:00	Rachel Ward	Associate Professor of Mathematics, University of Texas at Austin	Concentration inequalities for products of independent matrices
12:30	Lunch Break	2nd Floor of Shriver Hall
Session 3
14:00	Joan Bruna	Assistant Professor of Computer Science, Courant Institute and Center for Data Science, NYU	Mathematics of Deep Learning: myths, truths and enigmas
14:30	Anna Gilbert	Herman H. Goldstine Collegiate Professor of Mathematics, University of Michigan	Learning Metric Representations: Theory and Applications
15:00	Jeremias Sulam	Assistant Professor of Biomedical Engineering, Johns Hopkins University	Sparse Priors in Neural Architectures
15:15	Chong You	Postdoctoral Researcher, University of California, Berkeley	Sparse Methods for Learning Multiple Subspaces from Large-scale, Corrupted and Imbalanced Data
15:30	Coffee Break
Session 4
16:00	Amit Singer	Professor Department of Mathematics, Princeton University	Mathematics of Cryo-Electron Microscopy
16:30	Charles Meneveau	Louis M. Sardella Professor in Mechanical Engineering, Associate Director of IDIES, Johns Hopkins University	Fluid Turbulence and Learning from Big Numerical Data Sets
17:00	Archana Venkataraman	John C. Malone Assistant Professor of Electrical Engineering, Johns Hopkins University	Generative-Deep Hybrids for Decoding the Brain
17:15	Closing