Benjamin Aubin

According to our database, Benjamin Aubin authored at least 12 papers between 2018 and 2024.

Collaborative distances:

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

2024

Controllable Shadow Generation with Single-Step Diffusion Models from Synthetic Data.

Onur Tasar, Clément Chadebec, Benjamin Aubin

CoRR, 2024

Flash Diffusion: Accelerating Any Conditional Diffusion Model for Few Steps Image Generation.

Clément Chadebec, Onur Tasar, Eyal Benaroche, Benjamin Aubin

CoRR, 2024

2023

Tree-AMP: Compositional Inference with Tree Approximate Message Passing.

Antoine Baker, Florent Krzakala, Benjamin Aubin, Lenka Zdeborová

J. Mach. Learn. Res., 2023

2021

The Spiked Matrix Model With Generative Priors.

Benjamin Aubin, Bruno Loureiro, Antoine Maillard, Florent Krzakala, Lenka Zdeborová

IEEE Trans. Inf. Theory, 2021

Mean-field methods and algorithmic perspectives for high-dimensional machine learning.

Benjamin Aubin

CoRR, 2021

Linear unit-tests for invariance discovery.

Benjamin Aubin, Agnieszka Slowik, Martín Arjovsky, Léon Bottou, David Lopez-Paz

CoRR, 2021

2020

Mean-field methods and algorithmic perspectives for high-dimensional machine learning. (Méthodes à champ moyen et perspectives algorithmiques pour l'apprentissage automatique en haute dimension).

Benjamin Aubin

PhD thesis, 2020

TRAMP: Compositional Inference with TRee Approximate Message Passing.

Antoine Baker, Benjamin Aubin, Florent Krzakala, Lenka Zdeborová

CoRR, 2020

Generalization error in high-dimensional perceptrons: Approaching Bayes error with convex optimization.

Benjamin Aubin, Florent Krzakala, Yue M. Lu, Lenka Zdeborová

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

Exact asymptotics for phase retrieval and compressed sensing with random generative priors.

Benjamin Aubin, Bruno Loureiro, Antoine Baker, Florent Krzakala, Lenka Zdeborová

Proceedings of Mathematical and Scientific Machine Learning, 2020

Rademacher complexity and spin glasses: A link between the replica and statistical theories of learning.

Alia Abbara, Benjamin Aubin, Florent Krzakala, Lenka Zdeborová

Proceedings of Mathematical and Scientific Machine Learning, 2020

2018

The committee machine: Computational to statistical gaps in learning a two-layers neural network.

Benjamin Aubin, Antoine Maillard, Jean Barbier, Florent Krzakala, Nicolas Macris, Lenka Zdeborová

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018