Pierre Ablin
École Normale Supérieure
H-index: 16
Europe-France
Top articles of Pierre Ablin
Enhancing Hypergradients Estimation: A Study of Preconditioning and Reparameterization
arXiv preprint arXiv:2402.16748
2024/2/26
How to compute Hessian-vector products?
2024/2/16
Pierre Ablin
H-Index: 7
Careful with that Scalpel: Improving Gradient Surgery with an EMA
arXiv preprint arXiv:2402.02998
2024/2/5
James Thornton
H-Index: 0
Pierre Ablin
H-Index: 7
Specialized Language Models with Cheap Inference from Limited Domain Data
arXiv preprint arXiv:2402.01093
2024/2/2
Pierre Ablin
H-Index: 7
Understanding the Regularity of Self-Attention with Optimal Transport
arXiv preprint arXiv:2312.14820
2023/12/22
Pierre Ablin
H-Index: 7
Gabriel Peyré
H-Index: 46
Bilevel Optimization to Learn Training Distributions for Language Modeling under Domain Shift
2023/12/7
Pierre Ablin
H-Index: 7
Adaptive Training Distributions with Scalable Online Bilevel Optimization
arXiv preprint arXiv:2311.11973
2023/11/20
Pierre Ablin
H-Index: 7
A Challenge in Reweighting Data with Bilevel Optimization
arXiv preprint arXiv:2310.17386
2023/10/26
Anastasia Ivanova
H-Index: 30
Pierre Ablin
H-Index: 7
Optimization without retraction on the random generalized Stiefel manifold for canonical correlation analysis
2023/10/13
MultiView Independent Component Analysis with Delays
2023/9/17
Pierre Ablin
H-Index: 7
How to Scale Your EMA
Advances in Neural Information Processing Systems
2023/7/25
Pierre Ablin
H-Index: 7
Learning costs for structured monge displacements
arXiv preprint arXiv:2306.11895
2023/6/20
Pierre Ablin
H-Index: 7
Jonathan Niles-Weed
H-Index: 16
Test like you Train in Implicit Deep Learning
arXiv preprint arXiv:2305.15042
2023/5/24
Pierre Ablin
H-Index: 7
Gabriel Peyré
H-Index: 46
Infeasible deterministic, stochastic, and variance-reduction algorithms for optimization under orthogonality constraints
arXiv preprint arXiv:2303.16510
2023/3/29
Monge, Bregman and Occam: Interpretable Optimal Transport in High-Dimensions with Feature-Sparse Maps
Proceedings of the 40th International Conference on Machine Learning
2023/2/8
Pierre Ablin
H-Index: 7
A Lower Bound and a Near-Optimal Algorithm for Bilevel Empirical Risk Minimization
arXiv preprint arXiv:2302.08766
2023/2
Pierre Ablin
H-Index: 7
Fast and accurate optimization on the orthogonal manifold without retraction
2022/5/3
Pierre Ablin
H-Index: 7
Gabriel Peyré
H-Index: 46
A framework for bilevel optimization that enables stochastic and global variance reduction algorithms
Advances in Neural Information Processing Systems
2022/1/31
Pierre Ablin
H-Index: 7
Optimization flows landing on the Stiefel manifold⋆
IFAC-PapersOnLine
2022/1/1
Benchopt: Reproducible, efficient and collaborative optimization benchmarks
Advances in Neural Information Processing Systems
2022/12/6