← Authors

Pierre Ablin

29 papers · 2019–2025 · 5 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird πŸ—ΊοΈ Taxonomy Completionist (10) 🧭 Keyword Pioneer 🌍 Conference Polyglot (5) πŸƒ Academic Marathon (6) 🐝 Cross-Pollinator (12) 🌈 Renaissance Researcher (6) πŸŒ‰ Interdisciplinary Bridge πŸ‘₯ Mega-Team (21) ⚑ Prolific Year (7) ❓ The Questioner (2) πŸ”₯ Unstoppable (7) πŸ’Ž Century Club (29) πŸ—ƒοΈ Keyword Collector (99)

Conferences

ICML (10) NIPS (9) AISTATS (5) ICLR (3) JMLR (2)

Top co-authors

Alexandre Gramfort (7) Gabriel PeyrΓ© (7) Thomas Moreau (5) Marco Cuturi (5) David Grangier (4) Mathieu DagrΓ©ou (3) Eugene Ndiaye (3) Samuel Vaiter (3) Hugo Richard (3) Dan Busbridge (3)

Keywords

stochastic optimization (3) independent component analysis (3) probabilistic modeling (2) optimal transport (2) residual neural network (2) bilevel optimization (2) bayesian inference (1) feature selection (1) transformer architecture (1) source separation (1) gradient estimation (1) sparse representation (1) logistic regression (1) self-supervised learning (1) numerical optimization (1) natural language processing (1) sample complexity (1) automatic differentiation (1) attention mechanism (1) sparse coding (1)

Papers

The AdEMAMix Optimizer: Better, Faster, Older ICLR 2025
Shielded Diffusion: Generating Novel and Diverse Images using Sparse Repellency ICML 2025
Scaling Laws for Forgetting during Finetuning with Pretraining Data Injection ICML 2025
Soup-of-Experts: Pretraining Specialist Models via Parameters Averaging ICML 2025
Theory, Analysis, and Best Practices for Sigmoid Self-Attention ICLR 2025
Task-Adaptive Pretrained Language Models via Clustered-Importance Sampling ICLR 2025
Infeasible Deterministic, Stochastic, and Variance-Reduction Algorithms for Optimization under Orthogonality Constraints JMLR 2024
Learning Elastic Costs to Shape Monge Displacements NIPS 2024
A Lower Bound and a Near-Optimal Algorithm for Bilevel Empirical Risk Minimization AISTATS 2024
Enhancing Hypergradients Estimation: A Study of Preconditioning and Reparameterization AISTATS 2024
How Smooth Is Attention? ICML 2024
Careful with that Scalpel: Improving Gradient Surgery with an EMA ICML 2024
Optimization without Retraction on the Random Generalized Stiefel Manifold ICML 2024
How to Scale Your EMA NIPS 2023
Monge, Bregman and Occam: Interpretable Optimal Transport in High-Dimensions with Feature-Sparse Maps ICML 2023
A framework for bilevel optimization that enables stochastic and global variance reduction algorithms NIPS 2022
Benchopt: Reproducible, efficient and collaborative optimization benchmarks NIPS 2022
Do Residual Neural Networks discretize Neural Ordinary Differential Equations? NIPS 2022
Fast and accurate optimization on the orthogonal manifold without retraction AISTATS 2022
Sinkformers: Transformers with Doubly Stochastic Attention AISTATS 2022
Momentum Residual Neural Networks ICML 2021
Shared Independent Component Analysis for Multi-Subject Neuroimaging NIPS 2021
mvlearn: Multiview Machine Learning in Python JMLR 2021
Kernel Stein Discrepancy Descent ICML 2021
Modeling Shared responses in Neuroimaging Studies through MultiView ICA NIPS 2020
Super-efficiency of automatic differentiation for functions defined as a minimum ICML 2020
Stochastic algorithms with descent guarantees for ICA AISTATS 2019
Learning step sizes for unfolded sparse coding NIPS 2019
Manifold-regression to predict from MEG/EEG brain signals without source modeling NIPS 2019