Elvis Dohmatob

According to our database, Elvis Dohmatob authored at least 41 papers between 2013 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2024

Model Collapse Demystified: The Case of Regression.

Elvis Dohmatob, Yunzhen Feng, Julia Kempe

CoRR, 2024

A Tale of Tails: Model Collapse as a Change of Scaling Laws.

Elvis Dohmatob, Yunzhen Feng, Pu Yang, François Charton, Julia Kempe

CoRR, 2024

2023

Scaling Laws for Associative Memories.

Vivien Cabannes, Elvis Dohmatob, Alberto Bietti

CoRR, 2023

Robust Linear Regression: Phase-Transitions and Precise Tradeoffs for General Norms.

Elvis Dohmatob, Meyer Scetbon

CoRR, 2023

Contextual bandits with concave rewards, and an application to fair ranking.

Virginie Do, Elvis Dohmatob, Matteo Pirotta, Alessandro Lazaric, Nicolas Usunier

Proceedings of the Eleventh International Conference on Learning Representations, 2023

Robust Linear Regression: Gradient-descent, Early-stopping, and Beyond.

Meyer Scetbon, Elvis Dohmatob

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2023

Origins of Low-Dimensional Adversarial Perturbations.

Elvis Dohmatob, Chuan Guo, Morgane Goibert

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2023

2022

An Adversarial Robustness Perspective on the Topology of Neural Networks.

Morgane Goibert, Thomas Ricatte, Elvis Dohmatob

CoRR, 2022

On the (Non-)Robustness of Two-Layer Neural Networks in Different Learning Regimes.

Elvis Dohmatob, Alberto Bietti

CoRR, 2022

Scalable MCMC Sampling for Nonsymmetric Determinantal Point Processes.

Insu Han, Mike Gartrell, Elvis Dohmatob, Amin Karbasi

Proceedings of the International Conference on Machine Learning, 2022

Scalable Sampling for Nonsymmetric Determinantal Point Processes.

Insu Han, Mike Gartrell, Jennifer Gillenwater, Elvis Dohmatob, Amin Karbasi

Proceedings of the Tenth International Conference on Learning Representations, 2022

Fast online ranking with fairness of exposure.

Nicolas Usunier, Virginie Do, Elvis Dohmatob

Proceedings of the FAccT '22: 2022 ACM Conference on Fairness, Accountability, and Transparency, Seoul, Republic of Korea, June 21, 2022

2021

Brain topography beyond parcellations: Local gradients of functional maps.

Elvis Dohmatob, Hugo Richard, Ana Luísa Pinho, Bertrand Thirion

NeuroImage, 2021

Fundamental tradeoffs between memorization and robustness in random features and neural tangent regimes.

Elvis Dohmatob

CoRR, 2021

Scalable Learning and MAP Inference for Nonsymmetric Determinantal Point Processes.

Mike Gartrell, Insu Han, Elvis Dohmatob, Jennifer Gillenwater, Victor-Emmanuel Brunel

Proceedings of the 9th International Conference on Learning Representations, 2021

2020

Implicit bias of any algorithm: bounding bias via margin.

Elvis Dohmatob

CoRR, 2020

Universal Lower-Bounds on Classification Error under Adversarial Attacks and Random Corruption.

Elvis Dohmatob

CoRR, 2020

Learning disconnected manifolds: a no GANs land.

Ugo Tanielian, Thibaut Issenhuth, Elvis Dohmatob, Jérémie Mary

CoRR, 2020

On the Convergence of Smooth Regularized Approximate Value Iteration Schemes.

Elena Smirnova, Elvis Dohmatob

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Learning disconnected manifolds: a no GAN's land.

Ugo Tanielian, Thibaut Issenhuth, Elvis Dohmatob, Jérémie Mary

Proceedings of the 37th International Conference on Machine Learning, 2020

Distributionally Robust Counterfactual Risk Minimization.

Louis Faury, Ugo Tanielian, Elvis Dohmatob, Elena Smirnova, Flavian Vasile

Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020

2019

On the Convergence of Approximate and Regularized Policy Iteration Schemes.

Elena Smirnova, Elvis Dohmatob

CoRR, 2019

Adversarial Robustness via Adversarial Label-Smoothing.

Morgane Goibert, Elvis Dohmatob

CoRR, 2019

Distributionally Robust Reinforcement Learning.

Elena Smirnova, Elvis Dohmatob, Jérémie Mary

CoRR, 2019

Learning Nonsymmetric Determinantal Point Processes.

Mike Gartrell, Victor-Emmanuel Brunel, Elvis Dohmatob, Syrine Krichene

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Generalized No Free Lunch Theorem for Adversarial Robustness.

Elvis Dohmatob

Proceedings of the 36th International Conference on Machine Learning, 2019

2018

Continuation of Nesterov's Smoothing for Regression With Structured Sparsity in High-Dimensional Neuroimaging.

Fouad Hadj-Selem, Tommy Löfstedt, Elvis Dohmatob, Vincent Frouin, Mathieu Dubois, Vincent Guillemot, Edouard Duchesnay

IEEE Trans. Medical Imaging, 2018

Deep Determinantal Point Processes.

Mike Gartrell, Elvis Dohmatob

CoRR, 2018

Limitations of adversarial robustness: strong No Free Lunch Theorem.

Elvis Dohmatob

CoRR, 2018

2017

Enhancement of functional brain connectome analysis by the use of deformable models in the estimation of spatial decompositions of the brain images. (Amélioration de connectivité fonctionnelle par utilisation de modèles déformables dans l'estimation de décompositions spatiales des images de cerveau).

Elvis Dohmatob

PhD thesis, 2017

2016

Learning brain regions via large-scale online structured sparse dictionary learning.

Elvis Dohmatob, Arthur Mensch, Gaël Varoquaux, Bertrand Thirion

Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 2016

Multivariate hurst exponent estimation in FMRI. Application to brain decoding of perceptual learning.

Hubert Pelle, Philippe Ciuciu, Mehdi Rahim, Elvis Dohmatob, Patrice Abry, Virginie van Wassenhove

Proceedings of the 13th IEEE International Symposium on Biomedical Imaging, 2016

Local Q-linear convergence and finite-time active set identification of ADMM on a class of penalized regression problems.

Elvis Dohmatob, Michael Eickenberg, Bertrand Thirion, Gaël Varoquaux

Proceedings of the 2016 IEEE International Conference on Acoustics, 2016

2015

FAASTA: A fast solver for total-variation regularization of ill-conditioned problems with application to brain imaging.

Gaël Varoquaux, Michael Eickenberg, Elvis Dohmatob, Bertrand Thirion

CoRR, 2015

A simple and efficient algorithm for computing approximate Nash equilibria in two-person zero-sum sequential games with imcomplete information.

Elvis Dohmatob

CoRR, 2015

Speeding-Up Model-Selection in Graphnet via Early-Stopping and Univariate Feature-Screening.

Elvis Dohmatob, Michael Eickenberg, Bertrand Thirion, Gaël Varoquaux

Proceedings of the 2015 International Workshop on Pattern Recognition in NeuroImaging, 2015

Integrating Multimodal Priors in Predictive Models for the Functional Characterization of Alzheimer's Disease.

Mehdi Rahim, Bertrand Thirion, Alexandre Abraham, Michael Eickenberg, Elvis Dohmatob, Claude Comtat, Gaël Varoquaux

Proceedings of the Medical Image Computing and Computer-Assisted Intervention - MICCAI 2015, 2015

Grouping Total Variation and Sparsity: Statistical Learning with Segmenting Penalties.

Michael Eickenberg, Elvis Dohmatob, Bertrand Thirion, Gaël Varoquaux

Proceedings of the Medical Image Computing and Computer-Assisted Intervention - MICCAI 2015, 2015

2014

Region segmentation for sparse decompositions: better brain parcellations from rest fMRI.

Alexandre Abraham, Elvis Dohmatob, Bertrand Thirion, Dimitris Samaras, Gaël Varoquaux

CoRR, 2014

Benchmarking solvers for TV-ℓ1 least-squares and logistic regression in brain imaging.

Elvis Dopgima Dohmatob, Alexandre Gramfort, Bertrand Thirion, Gaël Varoquaux

Proceedings of the International Workshop on Pattern Recognition in Neuroimaging, 2014

2013

Extracting Brain Regions from Rest fMRI with Total-Variation Constrained Dictionary Learning.

Alexandre Abraham, Elvis Dohmatob, Bertrand Thirion, Dimitris Samaras, Gaël Varoquaux

Proceedings of the Medical Image Computing and Computer-Assisted Intervention - MICCAI 2013, 2013