Hemant Tyagi (2012)

Internship project topic:

Low dimensional models for high dimensional data.

Biography

Hemant received a master degree in Communication Systems from EPFL in 2011 with a thesis titles “Local sampling analysis for quadratic embeddings of Riemmanian manifold”. He is currently pursuing a PhD in Prof. Emo Welzs’s research group. His research interestes are approximation theory, online optimization, computational learning theory and low dimensional models for high dimensional data.

Publications (most recent)

Sparse non-negative super-resolution – simplified and stabilised

A. Eftekhari; J. Tanner; A. Thompson; B. Toader; H. Tyagi 

Applied And Computational Harmonic Analysis. 2021-01-01. Vol. 50, p. 216-280. DOI : 10.1016/j.acha.2019.08.004.

Learning non-parametric basis independent models from point queries via low-rank methods

H. Tyagi; V. Cevher 

Applied And Computational Harmonic Analysis. 2014. Vol. 37, num. 3, p. 389-412. DOI : 10.1016/j.acha.2014.01.002.

Tangent Space Estimation Bounds for Smooth Manifolds

H. Tyagi; E. Vural; P. Frossard 

2013. SAMPTA, July, 2013.

Tangent space estimation for smooth embeddings of Riemannian manifolds

H. Tyagi; E. Vural; P. Frossard 

Information and Inference: A Journal of the IMA. 2013. Vol. 2, num. 1, p. 69-114. DOI : 10.1093/imaiai/iat003.

Learning Ridge Functions With Randomized Sampling In High Dimensions

H. Tyagi; V. Cevher 

2012. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Kyoto, Japan, March 25-39, 2012. p. 2025-2028. DOI : 10.1109/ICASSP.2012.6288306.