Ph.D. student, Electrical Engineering and Computer Sciences, UC Berkeley. Advised by Michael I. Jordan. I am also a member of the Berkeley Artificial Intelligence Research Group. |

Contact

University of California, Berkeley 465 Soda Hall (AMPlab) Berkeley, CA 94720-1720 Email me at elalaoui at eecs dot berkeley dot edu

I am broadly interested in mathematical statistics, probability theory, and optimization theory. The questions that drive my research are the fundamental limitations of extracting information from noisy data and the algorithmic feasibility considerations surrounding this task. I tend to focus on simple, often idealized models where answers to the above questions admit sharp characterizations as the dimension of the problem grows unbounded. In many situations of this sort, a crisp -but often conjectural- picture of these characterizations has been brought forth by Statistical Physicists. I currently spend my time trying to gain insight from the Physics methods and put their predictions on a rigorous mathematical basis.

A. El Alaoui, F. Krzakala:

*Estimation in the Spiked Wigner Model: A Short Proof of the Replica Formula*. In preparation.

A. El Alaoui, F. Krzakala, M. I. Jordan:

*Finite-Size Corrections and Likelihood Ratio Fluctuations in the Spiked Wigner Model*. Submitted 2017. [arxiv].

M. Simchowitz, A. El Alaoui, B. Recht:

*On the Gap Between Strict-Saddles and True Convexity: An Omega(log d) Lower Bound for Eigenvector Approximation*. Submitted 2017 [arxiv].

A. El Alaoui, A. Ramdas, F. Krzakala, L. Zdeborová, M. I. Jordan:

*Decoding from Pooled data: Phase Transitions of Message Passing*. Short version in ISIT 2017. [arxiv].

A. El Alaoui, A. Ramdas, F. Krzakala, L. Zdeborová, M. I. Jordan:

*Decoding from Pooled data: Sharp Information-Theoretic Bounds*. Submitted 2016 [arxiv].

A. El Alaoui, X. Cheng, A. Ramdas, M. J. Wainwright, M. I. Jordan:

*Asymptotic behavior of Lp-based Laplacian regularization in semi-supervised learning*. COLT 2016 [proc., arxiv].

A. El Alaoui, M. W. Mahoney:

*Fast Randomized Kernel Ridge Regression With Statistical Guarantees*. NIPS 2015 [proc., arxiv].

CS174 Combinatorics and Discrete Probability (spring 2015).

STAT210B Theoretical Statistics, part B (spring 2017).

I am a fifth year Ph.D. student in Electrical Engineering and Computer Science at the University of California at Berkeley. I did my master's at Ecole Normale Supérieure and my undergrad at Ecole Polytechnique. I wrote my master's dissertation on probabilistic record linkage while working at Ecole des Ponts with Guillaume Obozinski.

M.Sc.

*Mathématiques, Vision et Apprentissage*, Ecole Normale Supérieure/Ecole des Ponts Paristech, 2013.Eng.Deg. Applied math, Ecole Polytechnique, 2012.