Soufiane Hayou
12 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 ↓+4 more ↓ Show less ↑
🗺️ Taxonomy Completionist (17) 🌍 Conference Polyglot · Silver 🏃 Academic Marathon · Sprint 🐣 Hot Topic Early Bird 👑 Triple Crown
🧬
Topic Evolution
🔥
Unstoppable · Bronze
💎
Century Club · Bronze
⚡
Prolific Year · Productive
Top co-authors
Research topics
Keywords
neural network optimization
(3)
deep neural network
(3)
learning rate
(2)
neural network
(2)
infinite-width limit
(2)
feature learning
(2)
low-rank adaptation
(2)
infinite depth limit
(2)
residual network
(2)
signal propagation
(2)
neural network theory
(1)
random matrix theory
(1)
covariance structure
(1)
phase transition
(1)
neural network training
(1)
perturbation analysis
(1)
hyperparameter transfer
(1)
synthetic data
(1)
label noise
(1)
weight initialization
(1)
Papers
Maximizing the Potential of Synthetic Data: Insights from Random Matrix Theory
ICLR 2025
Commutative Scaling of Width and Depth in Deep Neural Networks
JMLR 2024
Leave-one-out Distinguishability in Machine Learning
ICLR 2024
LoRA+: Efficient Low Rank Adaptation of Large Models
ICML 2024
Tensor Programs VI: Feature Learning in Infinite Depth Neural Networks
ICLR 2024
The Impact of Initialization on LoRA Finetuning Dynamics
NeurIPS 2024
Width and Depth Limits Commute in Residual Networks
ICML 2023
Feature Learning and Signal Propagation in Deep Neural Networks
ICML 2022
Regularization in ResNet with Stochastic Depth
NeurIPS 2021
Robust Pruning at Initialization
ICLR 2021
Stable ResNet
AISTATS 2021
On the Impact of the Activation function on Deep Neural Networks Training
ICML 2019