Email: elalaoui [at] cornell [dot] edu.   Office: 1176 Comstock Hall.

Research interests: High-dimensional phenomena in statistics and probability theory. Related algorithmic questions. Statistical physics.

The questions that drive my research are the fundamental limits of extracting information from noisy data, and the algorithmic feasibility of this task. I like to think about large random structures such as matrices, graphs and tensors, and understand how sudden changes in their structural properties have statistical and algorithmic consequences.

Preprints

  • Bounds on the covariance matrix of the Sherrington-Kirkpatrick model.
    With J. Gaitonde.
    Preprint 2022. [arxiv].
  • Efficient Z_2 synchronization on Z^d under symmetry-preserving side information.
    Preprint 2021. [arxiv].
  • Algorithmic thresholds in mean-field spin glasses.
    With A. Montanari.
    Preprint 2020. [arxiv].
  • Imputation for high-dimensional linear regression.
    With K. Chandrasekher and A. Montanari.
    Preprint 2020. [arxiv].

Published/accepted papers

  • Local algorithms for Maximum Cut and Minimum Bisection on locally treelike regular graphs of large degree.
    With A. Montanari and M. Sellke.
    Random Structures and Algorithms (to appear). [arxiv].
  • The Franz-Parisi Criterion and Computational Trade-offs in High Dimensional Statistics.
    With A. Bandeira, S. Hopkins, T. Schramm, A. Wein and I. Zadik.
    NeurIPS 2022 (oral presentation). [arxiv].
  • Sampling from the Sherrington-Kirkpatrick Gibbs measure via algorithmic stochastic localization.
    With A. Montanari and M. Sellke.
    63th Annual Conference on Foundations of Computer Science (Accepted 2022). [arxiv].
  • Algorithmic pure states for the negative spherical perceptron.
    With M. Sellke.
    Journal of Statistical Physics, Vol. 189, Article number 27, 2022. [journal, arxiv].
  • An Information-theoretic view of Stochastic Localization.
    With A. Montanari.
    IEEE Transactions on Information Theory (Accepted 2022). [journal, arxiv].
  • Optimization of mean-field spin glasses.
    With A. Montanari and M. Sellke.
    Annals of Probability, Vol. 49, No. 6, 2922-2960, 2021. [journal, arxiv].
  • On the computational tractability of statistical estimation on amenable graphs.
    With A. Montanari.
    Probability Theory and Related Fields, 181, 815–864, 2021. [journal, arxiv].
  • Fundamental limits of detection in the spiked Wigner model.
    With F. Krzakala and M. I. Jordan.
    Annals of Statistics, Vol 48, No. 2, 863-885, 2020. [journal, arxiv].
    Based on an earlier manuscript (unpublished) containing additional results about finite-size corrections.
  • The Kikuchi hierarchy and tensor PCA.
    With A. Wein and C. Moore.
    60th Annual Conference on Foundations of Computer Science (FOCS) 2019. [arxiv].
  • Decoding from pooled data: Sharp information-theoretic bounds.
    With A. Ramdas, F. Krzakala, L. Zdeborová and M. I. Jordan.
    SIAM Journal on Mathematics of Data Science 1-1 (2019), pp. 161-188. [journal, arxiv].
  • Decoding from pooled data: Phase transitions of message passing.
    With A. Ramdas, F. Krzakala, L. Zdeborová and M. I. Jordan.
    IEEE Transactions on Information Theory, 65, 572-585, 2019. [journal, arxiv]. Presented at IEEE International Symposium on Information Theory (ISIT) 2017. [proc.].
  • Detection limits in the high-dimensional spiked rectangular model.
    With M. I. Jordan.
    31th Annual Conference on Learning Theory (COLT), PMLR 75:410-438, 2018. [proc., arxiv].
  • Tight query complexity lower bounds for PCA via finite sample deformed Wigner law.
    With M. Simchowitz and B. Recht.
    50th Annual Symposium on the Theory of Computing (STOC) 2018. [proc., arxiv].
    An earlier version (not intended for publication) with slightly suboptimal results.
  • Estimation in the spiked Wigner model: A short proof of the replica formula.
    With F. Krzakala.
    IEEE International Symposium on Information Theory (ISIT) 2018. [proc., arxiv].
  • Asymptotic behavior of Lp-based Laplacian regularization in semi-supervised learning.
    With X. Cheng, A. Ramdas, M. J. Wainwright and M. I. Jordan.
    29th Annual Conference on Learning Theory (COLT), PMLR 49:879-906, 2016. [proc., arxiv].
  • Fast randomized kernel ridge regression with statistical guarantees.
    With M. W. Mahoney.
    Advances in Neural Information Processing Systems (Neurips), 2015. [proc., arxiv].

Teaching

  • STSCI3080Probability models and Inference (Cornell, fall21, spring22).
  • STSCI6940 Topics in high-dimensional inference (Cornell, spring 2021).
  • STAT210B Theoretical Statistics, part B (UC Berkeley, spring 2017).
  • CS174 Combinatorics and Discrete Probability (UC Berkeley, spring 2015).

CV

  • (2021-) Assistant professor, Department of Statistics and Data Science, Cornell University.
  • (Fall 2020) Richard M. Karp Research Fellow, Simons Institute for the Theory of Computing, UC Berkeley.
  • (2018-2020) Postdoctoral researcher, Stanford University. Hosted by Andrea Montanari.
  • (2013-2018) Ph.D. Electrical Engineering and Computer Sciences, UC Berkeley. Advised by Michael I. Jordan.
  • (2012-2013) M.Sc. Mathématiques, Vision et Apprentissage, Ecole Normale Supérieure/Ecole des Ponts Paristech.
  • (2009-2012) Eng.Deg. Applied math, Ecole Polytechnique.

Ph.D. Thesis

  • Detection limits and fluctuation results in some spiked random matrix models and pooling of discrete data. [link].
    Ahmed El Alaoui.
    Ph.D. Thesis, Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, 2018.