Sampling Theory and Applications, 13th international conference

›8:30 (1h)

Robust and efficient identification of neural networks
Massimo Fornasier

› A22 Amphi Wegener

8:30 - 9:30 (1h)

Robust and efficient identification of neural networks

A22 Amphi Wegener

Massimo Fornasier

https://sampta2019.sciencesconf.org/data/program/Fornasier.pdf

›9:30 (30min)

Pause café

9:30 - 10:00 (30min)

Pause café

›10:00 (2h05)

Quantization (invited)
Sjoerd Dirksen & Rayan Saab

› A22 Amphi Wegener

10:00 - 12:05 (2h05)

Quantization (invited)

A22 Amphi Wegener

Sjoerd Dirksen & Rayan Saab

› Robust One-bit Compressed Sensing With Manifold Data - 10:00-10:25 (25min)

› One-Bit Sensing of Low-Rank and Bisparse Matrices - Simon Foucart, Texas A&M 10:25-10:50 (25min)

› Robust 1-Bit Compressed Sensing via Hinge Loss Minimization - Alexander Stollenwerk, TU Aachen 10:50-11:15 (25min)

› High-performance quantization for spectral super-resolution - Sinan Gunturk, New York University 11:15-11:40 (25min)

› On one-stage recovery for ΣΔ-quantized compressed sensing - Ozgur Yilmaz, University of British Columbia 11:40-12:05 (25min)

›10:00 (2h05)

Analyse de Fourier
Jeff Hogan

› A22 Amphi Edison

10:00 - 12:05 (2h05)

Analyse de Fourier

A22 Amphi Edison

Jeff Hogan

› Riesz bases of exponentials for partitions of intervals - 10:00-10:25 (25min)

› Computability of the Fourier Transform and ZFC - 10:25-10:50 (25min)

› Rearranged Fourier Series and Generalizations to Non-Commutative Groups - Armenak Petrosyan, Oak Ridge National Laboratory 10:50-11:15 (25min)

› Deterministic guarantees for L1 -reconstruction: A large sieve approach with geometric flexibility - Michael Speckbacher, Institut de Mathématiques de Bordeaux 11:15-11:40 (25min)

› A Clifford Construction of Multidimensional Prolate Spheroidal Wave Functions - Hamed Baghal Ghaffari, University of Newcastle 11:40-12:05 (25min)

›12:05 (1h25)

Déjeuner

12:05 - 13:30 (1h25)

Déjeuner

›13:30 (50min)

Deep Learning
Radu Balan

› A22 Amphi Wegener

13:30 - 14:20 (50min)

Deep Learning

A22 Amphi Wegener

Radu Balan

› Approximation in Lp(μ) with deep ReLU neural networks - Felix Voigtlaender, Katholische Universitat Eichstatt-Ingolstadt 13:30-13:55 (25min)

› Modeling Global Dynamics from Local Snapshots with Deep Generative Neural Networks - Scott Gigante, Yale University 13:55-14:20 (25min)

›13:30 (50min)

Problèmes inverses
Steven Casey

› A22 Amphi Edison

13:30 - 14:20 (50min)

Problèmes inverses

A22 Amphi Edison

Steven Casey

› Convergence Rates for Hölder-Windows in Filtered Back Projection - Matthias Beckmann, University of Hambourg 13:30-13:55 (25min)

› Dynamical Sampling with a Burst-like Forcing Term - Ilya Krishtal, Northern Illinois University 13:55-14:20 (25min)

›14:30 (1h05)

Learning from moments - Large-scale learning with the memory of a goldfish
Rémi Gribonval (and closing)

› A22 Amphi Wegener

14:30 - 15:35 (1h05)

Learning from moments - Large-scale learning with the memory of a goldfish

A22 Amphi Wegener

Rémi Gribonval (and closing)

https://sampta2019.sciencesconf.org/data/program/Gribonval.pdf