Phan-Minh Nguyen
3 papers · 2019–2021 · 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
Venues
Top co-authors
Research topics
Keywords
representation learning
(1)
stochastic gradient descent
(1)
mean field theory
(1)
global convergence
(1)
deep learning
(1)
asymptotic analysis
(1)
gradient descent
(1)
mean field
(1)
multilayer neural networks
(1)
phase transition
(1)
training dynamics
(1)
feed-forward network
(1)
neural network
(1)
weight-tied autoencoder
(1)
Papers
Global Convergence of Three-layer Neural Networks in the Mean Field Regime
ICLR 2021
Limiting fluctuation and trajectorial stability of multilayer neural networks with mean field training
NeurIPS 2021
On Random Deep Weight-Tied Autoencoders: Exact Asymptotic Analysis, Phase Transitions, and Implications to Training
ICLR 2019