Pierre Marion
10 papers · 2021–2025 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
🐝 Cross-Pollinator (9) 🗺️ Taxonomy Completionist (15) 🌍 Conference Polyglot (6) 🧭 Keyword Pioneer 🌈 Renaissance Researcher (6)
🌉
Interdisciplinary Bridge
💎
Century Club
(10)
Conferences
NIPS (4)
ICLR (2)
AISTATS (1)
COLT (1)
EMNLP (1)
JMLR (1)
Top co-authors
Keywords
gradient flow
(2)
neural ordinary differential equation
(2)
semantic parsing
(1)
global convergence
(1)
neural network optimization
(1)
reproducing kernel hilbert space
(1)
gradient descent
(1)
lipschitz continuity
(1)
knowledge graph
(1)
generalization bound
(1)
recurrent neural network
(1)
deep neural network
(1)
hessian eigenvalue
(1)
implicit regularization
(1)
learning dynamics
(1)
gradient vanishing
(1)
shallow neural network
(1)
neural differential equation
(1)
residual network
(1)
flat minima
(1)
Papers
Scaling ResNets in the Large-depth Regime
JMLR 2025
Implicit Diffusion: Efficient optimization through stochastic sampling
AISTATS 2025
Taking a Big Step: Large Learning Rates in Denoising Score Matching Prevent Memorization
COLT 2025
Attention layers provably solve single-location regression
ICLR 2025
Implicit regularization of deep residual networks towards neural ODEs
ICLR 2024
Deep linear networks for regression are implicitly regularized towards flat minima
NIPS 2024
Generalization bounds for neural ordinary differential equations and deep residual networks
NIPS 2023
Leveraging the two-timescale regime to demonstrate convergence of neural networks
NIPS 2023
Framing RNN as a kernel method: A neural ODE approach
NIPS 2021
Structured Context and High-Coverage Grammar for Conversational Question Answering over Knowledge Graphs
EMNLP 2021