Amir Zandieh

photo placeholder image +41 21 693 66 43

Date de naissance : 07.10.1991

INJ 110 (Bâtiment INJ)
Station 14
CH-1015 Lausanne

+41 21 693 66 43
Unité: THL4
Local: INJ 110

Site web:
Unité: EDIC

Données administratives


Machine Learning 
Compressive Sensing
Big Data


Autres publications

Random Fourier features for kernel ridge regression: Approximation bounds and statistical guarantees (ICML 2017)
Random Fourier feature is one of the most popular techniques for scaling up kernel methods, such as kernel ridge regression. In this paper, we take steps toward understanding the statistical properties of random Fourier features. Specifically, we approach random Fourier features from a spectral matrix approximation point of view, give tight bounds on the number of Fourier features required to achieve a spectral approximation, and show how spectral matrix approximation bounds imply statistical guarantees for kernel ridge regression.
International Conference on Machine Learning (ICML 2017)
A Universal Sampling Method for Reconstructing Signals with Simple Fourier Transforms (STOC 2019)
ACM SIGACT Symposium on Theory of Computing (STOC 2019)
Beyond 1/2-Approximation for Submodular Maximization on Massive Data Streams (ICML 2018)
International Conference on Machine Learning (ICML 2018)
Dimension-independent Sparse Fourier Transform (SODA 2019)
ACM-SIAM Symposium on Discrete Algorithms (SODA 2019)
An adaptive sublinear-time block sparse Fourier transform (STOC 2017)
ACM SIGACT Symposium on Theory of Computing (STOC 2017)