Pierre Marion
10 papers · 2021–2025 · 6 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 ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (23) 🐣 Hot Topic Early Bird 💎 Century Club · Bronze
🗃️
Keyword Collector
(51)
Top co-authors
Research topics
Machine Learning
(9)
Optimization & Theory · Machine Learning
(9)
Deep Learning
(6)
Architectures
(5)
Mathematics & Optimization
(3)
Core Methods
(3)
Optimization
(2)
Optimization & Theory · Deep Learning
(2)
Artificial Intelligence
(1)
Knowledge & Reasoning
(1)
Natural Language Processing
(1)
Applications
(1)
Bayesian & Probabilistic
(1)
Core AI
(1)
Mathematics
(1)
Keywords
gradient flow
(3)
implicit regularization
(2)
neural ordinary differential equation
(2)
residual network
(2)
global convergence
(2)
reproducing kernel hilbert space
(1)
neural network optimization
(1)
question answering
(1)
bilevel optimization
(1)
lipschitz continuity
(1)
knowledge graph
(1)
learning rate
(1)
generalization bound
(1)
recurrent neural network
(1)
hessian eigenvalue
(1)
implicit differentiation
(1)
deep neural network
(1)
gradient descent
(1)
semantic parsing
(1)
stochastic gradient descent
(1)
Papers
Attention layers provably solve single-location regression
ICLR 2025
Implicit Diffusion: Efficient optimization through stochastic sampling
AISTATS 2025
Scaling ResNets in the Large-depth Regime
JMLR 2025
Taking a Big Step: Large Learning Rates in Denoising Score Matching Prevent Memorization
COLT 2025
Deep linear networks for regression are implicitly regularized towards flat minima
NeurIPS 2024
Implicit regularization of deep residual networks towards neural ODEs
ICLR 2024
Generalization bounds for neural ordinary differential equations and deep residual networks
NeurIPS 2023
Leveraging the two-timescale regime to demonstrate convergence of neural networks
NeurIPS 2023
Framing RNN as a kernel method: A neural ODE approach
NeurIPS 2021
Structured Context and High-Coverage Grammar for Conversational Question Answering over Knowledge Graphs
EMNLP 2021