El Mehdi Achour
4 papers · 2022–2024 · 2 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 ↓
🌍
Conference Polyglot · Bronze
🐣
Hot Topic Early Bird
❓
The Questioner
Venues
Top co-authors
Research topics
Keywords
saddle point
(2)
matrix factorization
(1)
deep learning
(1)
loss landscape
(1)
energy landscape
(1)
predictive coding
(1)
optimization theory
(1)
fat-shattering dimension
(1)
mean squared error
(1)
matrix rank
(1)
gradient flow
(1)
linear network
(1)
approximation theory
(1)
linear neural network
(1)
deep linear network
(1)
orthogonality regularization
(1)
critical point
(1)
vanishing gradient
(1)
second-order analysis
(1)
feedforward neural network
(1)
Papers
Only Strict Saddles in the Energy Landscape of Predictive Coding Networks?
NeurIPS 2024
The Loss Landscape of Deep Linear Neural Networks: a Second-order Analysis
JMLR 2024
A general approximation lower bound in L^p norm, with applications to feed-forward neural networks
NeurIPS 2022
Existence, Stability and Scalability of Orthogonal Convolutional Neural Networks
JMLR 2022