ETH-FDS seminar series

More information about ETH Foundations of Data Science can be found here

Modal title

Modal content

Please subscribe here if you would you like to be notified about these presentations via e-mail. Moreover you can subscribe to the iCal/ics Calender.

Autumn Semester 2019

Date / Time

Speaker

Title

Location

7 October 2019
16:15-17:15

Gitta Kutyniok
TU Berlin

Event Details

ETH-FDS seminar

Title	Deep Learning meets Modeling: Taking the Best out of Both Worlds
Speaker, Affiliation	Gitta Kutyniok, TU Berlin
Date, Time	7 October 2019, 16:15-17:15
Location	HG G 19.2
Abstract	Speaker invited by: Christoph Schwab Inverse problems in imaging such as denoising, recovery of missing data, or the inverse scattering problem appear in numerous applications. However, due to their increasing complexity, model-based methods are often today not sufficient anymore. At the same time, we witness the tremendous success of data-based methodologies, in particular, deep neural networks for such problems. However, pure deep learning approaches often neglect known and valuable information from the modeling world and also currently still lack a profound theoretical understanding. In this talk, we will provide an introduction to this problem complex and then focus on the inverse problem of computed tomography, where one of the key issues is the limited angle problem. For this problem, we will demonstrate the success of hybrid approaches. We will develop a solver for this severely ill-posed inverse problem by combining the model-based method of sparse regularization by shearlets with the data-driven method of deep learning. Our approach is faithful in the sense that we only learn the part which cannot be handled by model-based methods, while applying the theoretically controllable sparse regularization technique to all other parts. We further show that our algorithm significantly outperforms previous methodologies, including methods entirely based on deep learning. Finally, we will discuss how similar ideas can also be used to solve related problems such as detection of wavefront sets.

Deep Learning meets Modeling: Taking the Best out of Both Worldsread_more

HG G 19.2

10 December 2019
16:15-17:15

Yue Lu
John A. Paulson School of Engineering and Applied Sciences, Harvard University

Event Details

ETH-FDS seminar

Title	Exploiting the Blessings of Dimensionality in Big Data
Speaker, Affiliation	Yue Lu, John A. Paulson School of Engineering and Applied Sciences, Harvard University
Date, Time	10 December 2019, 16:15-17:15
Location	HG E 1.2
Abstract	The massive datasets being compiled by our society present new challenges and opportunities to the field of signal and information processing. The increasing dimensionality of modern datasets offers many benefits. In particular, the very high-dimensional settings allow one to develop and use powerful asymptotic methods in probability theory and statistical physics to obtain precise characterizations that would otherwise be intractable in moderate dimensions. In this talk, I will present recent work where such blessings of dimensionality are exploited. In particular, I will show (1) the exact characterization of a widely-used spectral method for nonconvex statistical estimation; (2) the fundamental limits of solving the phase retrieval problem via linear programming; and (3) how to use scaling and mean-field limits to analyze nonconvex optimization algorithms for high-dimensional inference and learning. In these problems, asymptotic methods not only clarify some of the fascinating phenomena that emerge with high-dimensional data, they also lead to optimal designs that significantly outperform heuristic choices commonly used in practice.
Assets	Video Yue M. Lu - ETH-FDS talk on 10 December 2019file_download

Exploiting the Blessings of Dimensionality in Big Dataread_more

HG E 1.2

Archive: SS 24 AS 23 SS 23 AS 22 SS 22 AS 21 SS 21 AS 20 SS 20 AS 19 SS 19