Marwa El Halabi (2018)

Research Interests:

  • Convex optimization
  • Structured sparsity
  • Submodular and discrete optimization
  • Theoretical computer science


I received my diploma in Computer and Communication Engineering from the American University of Beirut in 2012. From September 2012 to August 2018 I was a doctoral assistant at EPFL. My PhD thesis, entitled Learning with Structured Sparsity: From Discrete to Convex and Back was supervised by Prof. Volkan Cevher.

Publications with LIONS (most recent)

Learning with Structured Sparsity: From Discrete to Convex and Back.

M. El Halabi / V. Cevher (Dir.)  

EPFL, 2018. 

Combinatorial Penalties: Which structures are preserved by convex relaxations?

M. El Halabi; F. Bach; V. Cevher 

2017. 21st International Conference on Artificial Intelligence and Statistics (AISTATS), Lanzarotte, Spain, April 9-11, 2017.

General Proximal Gradient Method: A Case for Non-Euclidean Norms

M. El Halabi; Y-P. Hsieh; B. Vu; Q. Nguyen; V. Cevher 


An Efficient Streaming Algorithm for the Submodular Cover Problem

A. Norouzi Fard; A. Bazzi; M. El Halabi; I. Bogunovic; Y-P. Hsieh et al. 

2016. The Thirtieth Annual Conference on Neural Information Processing Systems (NIPS).

Frank-Wolfe Works for Non-Lipschitz Continuous Gradient Objectives: Scalable Poisson Phase Retrieval

G. Odor; Y-H. Li; A. Yurtsever; Y-P. Hsieh; Q. Tran Dinh et al. 

2016. 41st IEEE International Conference on Acoustics, Speech and Signal Processing. p. 6230-6234. DOI : 10.1109/ICASSP.2016.7472875.