Emmanuel Abbé

EPFL SB MATH MDS1
MA C2 543 (Bâtiment MA)
Station 8
1015 Lausanne

EPFL IC IINFCOM MDS2
INR 112 (Bâtiment INR)
Station 14
1015 Lausanne

Mission

Chair of Mathematical Data Science (SB/IC)
The research in the chair of Mathematical Data Science (MDS) focuses on the mathematical principles that underpin the analysis and design of information and data science technologies. As branches of mathematics, this involves probability, statistics, and discrete mathematics, and as specific fields, machine learning and information theory.
Please consult http://deepfoundations.ai/ for postdoc applications.

Emmanuel Abbe received his Ph.D. degree from the EECS Department at the Massachusetts Institute of Technology (MIT) in 2008, and his M.S. degree from the Department of Mathematics at the Ecole Polytechnique Fédérale de Lausanne in 2003. He was at Princeton University as an assistant professor from 2012-2016 and an associate professor from 2016, jointly in the Program for Applied and Computational Mathematics and the Department of Electrical Engineering, as well an associate faculty in the Department of Mathematics at Princeton University since 2016. He joined EPFL in 2018 as a Full Professor, jointly in the Mathematics Institute and the School of Computer and Communication Sciences, where he holds the Chair of Mathematical Data Science.
He is the recipient of the Foundation Latsis International Prize, the Bell Labs Prize, the NSF CAREER Award, the Google Faculty Research Award, the Walter Curtis Johnson Prize, the von Neumann Fellowship from the Institute for Advanced Study, the IEEE Information Theory Society Paper Award, and a co-recipient of the Simons-NSF Mathematics of Deep Learning Collaborative Research Award.

Prof. E. Abbe is also a Global Expert at the Geneva Science and Diplomacy Anticipator (GESDA), a member of the Steering Committee of the Center for Intelligent Systems (CIS), EPFL, and director interim of the College des Sciences, EPFL.

Prix et distinctions

International Conference on Machine Learning (ICML)

2023

2020

Publications représentatives

On the power of differentiable learning versus PAC and SQ learning

E. Abbe, P. Kamath, E. Malach, C. Sandon, N. Srebro
Published in NeurIPS'21 Spotlight  in

The staircase property: how hierarchical structure can guide deep learning

E. Abbe, E. Boix-Adsera, M. Brenner, G. Bresler, D. Nagarj
Published in NeurIPS'21 in

Stochastic block model entropy and broadcasting on trees with survey

E. Abbe, E. Cornacchia, Y. Gu, Y. Polyanskiy
Published in COLT'21 Best Student Paper Award in

Quantifying the Benefit of Using Differentiable Learning over Tangent Kernels

E. Malach, P. Kamath, E. Abbe, N. Srebro
Published in ICML'21  in

Reed-Muller codes: theory and algorithms,

E. Abbe, A. Shpilka, M. Ye
Published in Information Theory Trans. in

On the universality of deep learning

E. Abbe, C. Sandon
Published in NeurIPS 20 in

Reed-Muller codes polarize

E. Abbe, M. Ye
Published in FOCS 19 in

Recursive projection-aggregation decoding of Reed-Muller codes

Min Ye, Emmanuel Abbe
Published in ISIT 19 in

Chaining Meets Chain Rule: Multilevel Entropic Regularization and Training of Neural Nets

Amir R. Asadi, Emmanuel Abbe
Published in JMLR in

Subadditivity Beyond Trees and the Chi-Squared Mutual Information

Emmanuel Abbe, Enric Boix-Adserà
Published in ISIT 19 in

Graph powering and spectral robustness

E. Abbe, E. Boix, P. Ralli, C. Sandon
Published in SIAM Journal on Mathematics of Data Science  in

An Information-Percolation Bound for Spin Synchronization on General Graphs

E. Abbe, E. Boix
Published in Annals of Applied Probability in

Chaining mutual information and tightening generalization bounds

A. Asadi, E. Abbe, S. Verdu
Published in NIPS 18 in

Group syncrhonization on grids

E. Abbe, L. Massoulié, A. Montanari, A. Sly, N. Srivastava
Published in Mathematical Statistics and Learning (MSL) 18 in

Communication-computation efficient gradient coding

M. Ye, E. Abbe
Published in ICML 18 in

Community Detection on Euclidean Random Graphs

A. Sankararaman, E. Abbe, F. Baccelli
Published in Information and Inference: A Journal of the IMA in

Multireference alignment is easier with an aperiodic translation distribution

E. Abbe, T. Bandory, W. Leeb, J. Pereira, N. Sharon, A. Singer
Published in Information Theory Trans. in

Entrywise eigenvector analysis of random matrices of low expected rank

E. Abbe, J. Fan, K. Wang, Y. Zhong
Published in Annals of Statistics in

Generalized nonbacktracking bounds on the influence

E. Abbe, S. Kulkarni, E. Lee
Published in JMLR in

Nonbacktracking bounds on the influence in cascade models

E. Abbe, S. Kulkarni, E. Lee
Published in NIPS 17 in

Sample complexity of the Boolean multireference alignment problem

E. Abbe, J. Pereira, A. Singer
Published in ISIT 16 in

Proof of the achievability conjectures in the general stochastic block model

E. Abbe, C. Sandon
Published in CPAM in

Reed-Muller codes for random erasures and erros

E. Abbe, A. Shpilka, A. Wigderson
Published in STOC 15 in

Asymptotic mutual information for the balanced binary SBM

Y. Desphande, E. Abbe, A. Montanari
Published in Journal Information and Inference: A Journal of the IMA in

High-girth matrices and polarization

E. Abbe, Y. Wigderson
Published in ISIT 15 in

Exact recovery in the stochastic block model

E. Abbe, A. Bandeira, G. Hall
Published in Information Theory Trans. in

 Linear Boolean classification, coding and "the critical problem"

E. Abbe, N. Alon, A. Bandeira
Published in ISIT 14 in

Decoding graph labels from censored correlations: phase transition and efficient recovery

E. Abbe, A. Bandeira, A. Bracher, A. Singer
Published in Transactions on Network Science and Eng. in

Conditional random fields, planted constraint satisfaction and entropy concentration

E. Abbe, A. Montanari
Published in Journal Theory of Computing in

On the concentration of the number of solutions of random satisfiability formulas

E. Abbe, A. Montanari
Published in Random Structures and Algorithms in

Polar codes for broadcast channels

N. Goela, E. Abbe, M. Gastpar
Published in Information Theory Trans. in

Privacy-preserving methods in systemic risk

E. Abbe, A. Khandani, A. W. Lo
Published in American Economical Review (AER) in

Enseignement et PhD

Doctorant·es actuel·les

Denys Pushkin, Ortal Yona Senouf, Vladyslav Shashkov

A dirigé les thèses EPFL de

Elisabetta Cornacchia, Aryo Lotfi

Cours