Edouard Oyallon

33
Documents
Contact

Publications

7
4
4
4
3
3
3
3
2
2
2
2
2
2
2
2
2
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1

Publications

Deposit thumbnail

PETRA: Parallel End-to-end Training with Reversible Architectures

Stéphane Rivaud , Louis Fournier , Thomas Pumir , Eugene Belilovsky , Michael Eickenberg et al.

The Thirteenth International Conference on Learning Representations, Apr 2025, Singapour, Singapore

Communication dans un congrès hal-04594647v2

DISCO: learning to DISCover an evolution Operator for multi-physics-agnostic prediction

Rudy Morel , Jiequn Han , Edouard Oyallon

International Conference on Machine Learning, Jul 2025, Vancouver, Canada

Communication dans un congrès hal-05083819v1
Deposit thumbnail

ACCO: Accumulate While You Communicate for Communication-Overlapped Sharded LLM Training

Adel Nabli , Louis Fournier , Pierre Erbacher , Louis Serrano , Eugene Belilovsky et al.

The Thirty-ninth Annual Conference on Neural Information Processing Systems, Dec 2025, San diego (Californie), United States

Communication dans un congrès hal-04592562v3
Deposit thumbnail

$\textbf{A}^2\textbf{CiD}^2$: Accelerating Asynchronous Communication in Decentralized Deep Learning

Adel Nabli , Eugene Belilovsky , Edouard Oyallon

Thirty-seventh Conference on Neural Information Processing Systems, Dec 2023, New Orleans, United States

Communication dans un congrès hal-04124318v2
Deposit thumbnail

Can Forward Gradient Match Backpropagation?

Louis Fournier , Stéphane Rivaud , Eugene Belilovsky , Michael Eickenberg , Edouard Oyallon

Fortieth International Conference on Machine Learning, Jul 2023, Honolulu (Hawaii), USA, United States

Communication dans un congrès hal-04119829v1
Deposit thumbnail

Preventing Dimensional Collapse in Contrastive Local Learning with Subsampling

Louis Fournier , Adeetya Patel , Michael Eickenberg , Edouard Oyallon , Eugene Belilovsky

ICML 2023 Workshop on Localized Learning (LLW), Jul 2023, Honolulu (Hawaii), USA, United States

Communication dans un congrès hal-04156218v1
Deposit thumbnail

DADAO: Decoupled Accelerated Decentralized Asynchronous Optimization

Adel Nabli , Edouard Oyallon

International Conference on Machine Learning, Jul 2023, Honolulu, United States

Communication dans un congrès hal-03737694v3
Deposit thumbnail

Why do tree-based models still outperform deep learning on typical tabular data?

Léo Grinsztajn , Edouard Oyallon , Gaël Varoquaux

36th Conference on Neural Information Processing Systems (NeurIPS 2022) Track on Datasets and Benchmarks, Nov 2022, New Orleans, United States

Communication dans un congrès hal-03723551v3
Deposit thumbnail

On Non-Linear operators for Geometric Deep Learning

Grégoire Sergeant-Perthuis , Jakob Maier , Joan Bruna , Edouard Oyallon

Conference on Neural Information Processing Systems (Neurips), Dec 2022, New Orleans, United States. ⟨10.48550/arXiv.2207.03485⟩

Communication dans un congrès hal-03711864v2
Deposit thumbnail

The Unreasonable Effectiveness of Patches in Deep Convolutional Kernels Methods

Louis Thiry , Michael Arbel , Eugene Belilovsky , Edouard Oyallon

International Conference on Learning Representation (ICLR 2021), 2021, Vienna (online), Austria

Communication dans un congrès hal-03114389v1
Deposit thumbnail

Low-Rank Projections of GCNs Laplacian

Nathan Grinsztajn , Philippe Preux , Edouard Oyallon

ICLR 2021 Workshop GTRL, May 2021, Online, France

Communication dans un congrès hal-03248056v1
Deposit thumbnail

Deep Reinforcement Learning for L3 Slice Localization in Sarcopenia Assessment

Othmane Laousy , Guillaume Chassagnon , Edouard Oyallon , Nikos Paragios , Marie-Pierre Revel et al.

Machine Learning in Medical Imaging @MICCAI, Sep 2021, Strasbourg, France. pp.317-326, ⟨10.1007/978-3-030-87589-3_33⟩

Communication dans un congrès hal-03532954v1

Decoupled Greedy Learning of CNNs

Eugene Belilovsky , Michael Eickenberg , Edouard Oyallon

International Conference on Machine Learning, Jul 2020, Vienna (virtual), Austria. pp.5368-5377

Communication dans un congrès hal-02945327v1
Deposit thumbnail

Interferometric Graph Transform: a Deep Unsupervised Graph Representation

Edouard Oyallon

37th International Conference on Machine Learning (ICML 2020), Jul 2020, Online, Austria

Communication dans un congrès hal-02862516v1
Deposit thumbnail

On Lazy Training in Differentiable Programming

Lenaic Chizat , Edouard Oyallon , Francis Bach

NeurIPS 2019 - 33rd Conference on Neural Information Processing Systems, Dec 2019, Vancouver, Canada. pp.2937-2947

Communication dans un congrès hal-01945578v6
Deposit thumbnail

Greedy Layerwise Learning Can Scale to ImageNet

Eugene Belilovsky , Michael Eickenberg , Edouard Oyallon

ICML 2019 - 36th International Conference on Machine Learning, Jun 2019, Long Beach, CA, United States

Communication dans un congrès hal-02119398v1
Deposit thumbnail

i-RevNet: Deep Invertible Networks

Jörn-Henrik Jacobsen , Arnold Smeulders , Edouard Oyallon

ICLR 2018 - International Conference on Learning Representations, Apr 2018, Vancouver, Canada

Communication dans un congrès hal-01712808v1
Deposit thumbnail

Nonlinear Acceleration of CNNs

Damien Scieur , Edouard Oyallon , Alexandre d'Aspremont , Francis Bach

ICLR Workshop track, Apr 2018, Vancouver, Canada

Communication dans un congrès hal-01805251v3
Deposit thumbnail

Compressing the Input for CNNs with the First-Order Scattering Transform

Edouard Oyallon , Eugene Belilovsky , Sergey Zagoruyko , Michal Valko

ECCV 2018 - European Conference on Computer Vision, Sep 2018, Munich, Germany

Communication dans un congrès hal-01850921v1
Deposit thumbnail

Scaling the Scattering Transform: Deep Hybrid Networks

Edouard Oyallon , Eugene Belilovsky , Sergey Zagoruyko

International Conference on Computer Vision (ICCV), Oct 2017, Venice, Italy

Communication dans un congrès hal-01495734v2
Deposit thumbnail

Analyzing and introducing structures in deep convolutional neural networks

Edouard Oyallon

Computer Vision and Pattern Recognition [cs.CV]. Université Paris sciences et lettres, 2017. English. ⟨NNT : 2017PSLEE060⟩

Thèse tel-03917151v2