Pierre Ablin
29 papers · 2019–2025 · 5 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+10 more ↓ Show less ↑
🗺️ Taxonomy Completionist (42) 🏃 Academic Marathon · Sprint 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Silver 🐣 Hot Topic Early Bird
👥
Mega-Team · Squad
🏆
Keyword Champion
(2)
🔬
Deep Specialist
(14)
🌈
Renaissance Researcher
(6)
🔥
Unstoppable · Bronze
❓
The Questioner
(2)
⚡
Prolific Year · Productive
💎
Century Club · Bronze
📈
Trend Setter
🗃️
Keyword Collector
(143)
Top co-authors
Research topics
Machine Learning
(28)
Optimization & Theory · Machine Learning
(18)
Mathematics & Optimization
(13)
Optimization
(12)
Deep Learning
(9)
Core Methods
(8)
Learning Types
(6)
Artificial Intelligence
(5)
Architectures
(5)
Core AI
(4)
Mathematics
(4)
Optimization & Theory · Deep Learning
(4)
Techniques
(4)
Natural Language Processing
(3)
Application Areas
(3)
Keywords
stochastic optimization
(4)
independent component analysis
(3)
bilevel optimization
(3)
specialist model
(2)
transformer architecture
(2)
attention mechanism
(2)
matrix multiplication
(2)
canonical correlation analysis
(2)
variance reduction
(2)
empirical risk minimization
(2)
multi-view learning
(2)
residual neural network
(2)
probabilistic modeling
(2)
language modeling
(2)
exponential moving average
(2)
optimal transport
(2)
feature selection
(1)
source separation
(1)
logistic regression
(1)
natural language processing
(1)
Papers
Scaling Laws for Forgetting during Finetuning with Pretraining Data Injection
ICML 2025
Shielded Diffusion: Generating Novel and Diverse Images using Sparse Repellency
ICML 2025
Soup-of-Experts: Pretraining Specialist Models via Parameters Averaging
ICML 2025
Task-Adaptive Pretrained Language Models via Clustered-Importance Sampling
ICLR 2025
The AdEMAMix Optimizer: Better, Faster, Older
ICLR 2025
Theory, Analysis, and Best Practices for Sigmoid Self-Attention
ICLR 2025
A Lower Bound and a Near-Optimal Algorithm for Bilevel Empirical Risk Minimization
AISTATS 2024
Careful with that Scalpel: Improving Gradient Surgery with an EMA
ICML 2024
Enhancing Hypergradients Estimation: A Study of Preconditioning and Reparameterization
AISTATS 2024
How Smooth Is Attention?
ICML 2024
Infeasible Deterministic, Stochastic, and Variance-Reduction Algorithms for Optimization under Orthogonality Constraints
JMLR 2024
Learning Elastic Costs to Shape Monge Displacements
NeurIPS 2024
Optimization without Retraction on the Random Generalized Stiefel Manifold
ICML 2024
How to Scale Your EMA
NeurIPS 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
NeurIPS 2022
Benchopt: Reproducible, efficient and collaborative optimization benchmarks
NeurIPS 2022
Do Residual Neural Networks discretize Neural Ordinary Differential Equations?
NeurIPS 2022
Fast and accurate optimization on the orthogonal manifold without retraction
AISTATS 2022
Sinkformers: Transformers with Doubly Stochastic Attention
AISTATS 2022
Kernel Stein Discrepancy Descent
ICML 2021
Momentum Residual Neural Networks
ICML 2021
mvlearn: Multiview Machine Learning in Python
JMLR 2021
Shared Independent Component Analysis for Multi-Subject Neuroimaging
NeurIPS 2021
Modeling Shared responses in Neuroimaging Studies through MultiView ICA
NeurIPS 2020
Super-efficiency of automatic differentiation for functions defined as a minimum
ICML 2020
Learning step sizes for unfolded sparse coding
NeurIPS 2019
Manifold-regression to predict from MEG/EEG brain signals without source modeling
NeurIPS 2019
Stochastic algorithms with descent guarantees for ICA
AISTATS 2019