Quynh Nguyen

27 papers A* 9Journal 15Unranked 3
YearRankTypeTitle / Venue / Authors
2021 J jnl
A Fully Rigorous Proof of the Derivation of Xavier and He's Initialization for Deep ReLU Networks.
CoRR
Quynh Nguyen
2021 J jnl
A Note on Connectivity of Sublevel Sets in Deep Learning.
CoRR
Quynh Nguyen
2021 J jnl
On Connectivity of Solutions in Deep Learning: The Role of Over-parameterization and Feature Quality.
CoRR
Quynh Nguyen, Pierre Bréchet, Marco Mondelli
2021 A* conf
On the Proof of Global Convergence of Gradient Descent for Deep ReLU Networks with Linear Widths.
ICML
Quynh Nguyen
2021 J jnl
On the Proof of Global Convergence of Gradient Descent for Deep ReLU Networks with Linear Widths.
CoRR
Quynh Nguyen
2021 A* conf
Tight Bounds on the Smallest Eigenvalue of the Neural Tangent Kernel for Deep ReLU Networks.
ICML
Quynh Nguyen, Marco Mondelli, Guido F. Montúfar
2021 A* conf
When Are Solutions Connected in Deep Networks?
NeurIPS
Quynh Nguyen, Pierre Bréchet, Marco Mondelli
2020 A* conf
Global Convergence of Deep Networks with One Wide Layer Followed by Pyramidal Topology.
NeurIPS
Quynh Nguyen, Marco Mondelli
2020 J jnl
Global Convergence of Deep Networks with One Wide Layer Followed by Pyramidal Topology.
CoRR
Quynh Nguyen, Marco Mondelli
2020 J jnl
Tight Bounds on the Smallest Eigenvalue of the Neural Tangent Kernel for Deep ReLU Networks.
CoRR
Quynh Nguyen, Marco Mondelli, Guido Montúfar
2019 A* conf
On Connected Sublevel Sets in Deep Learning.
ICML
Quynh Nguyen
2019 J jnl
On Connected Sublevel Sets in Deep Learning.
CoRR
Quynh Nguyen
2019 — conf
On the loss landscape of a class of deep neural networks with no bad local valleys.
ICLR (Poster)
Quynh Nguyen, Mahesh Chandra Mukkamala, Matthias Hein
2018 A* conf
Neural Networks Should Be Wide Enough to Learn Disconnected Decision Regions.
ICML
Quynh Nguyen, Mahesh Chandra Mukkamala, Matthias Hein
2018 J jnl
Neural Networks Should Be Wide Enough to Learn Disconnected Decision Regions.
CoRR
Quynh Nguyen, Mahesh Chandra Mukkamala, Matthias Hein
2018 J jnl
On the loss landscape of a class of deep neural networks with no bad local valleys.
CoRR
Quynh Nguyen, Mahesh Chandra Mukkamala, Matthias Hein
2018 A* conf
Optimization Landscape and Expressivity of Deep CNNs.
ICML
Quynh Nguyen, Matthias Hein
2018 — conf
The loss surface and expressivity of deep convolutional neural networks.
ICLR (Workshop)
Quynh Nguyen, Matthias Hein
2017 J jnl
An Efficient Multilinear Optimization Framework for Hypergraph Matching.
IEEE Trans. Pattern Anal. Mach. Intell.
Quynh Nguyen, Francesco Tudisco, Antoine Gautier, Matthias Hein
2017 A* conf
The Loss Surface of Deep and Wide Neural Networks.
ICML
Quynh Nguyen, Matthias Hein
2017 J jnl
The loss surface and expressivity of deep convolutional neural networks.
CoRR
Quynh Nguyen, Matthias Hein
2017 J jnl
The loss surface of deep and wide neural networks.
CoRR
Quynh Nguyen, Matthias Hein
2016 — conf
Globally Optimal Training of Generalized Polynomial Neural Networks with Nonlinear Spectral Methods.
NIPS
Antoine Gautier, Quynh Nguyen, Matthias Hein
2016 J jnl
Globally Optimal Training of Generalized Polynomial Neural Networks with Nonlinear Spectral Methods.
CoRR
Antoine Gautier, Quynh Nguyen, Matthias Hein
2016 A* conf
Latent Embeddings for Zero-Shot Classification.
CVPR
Yongqin Xian, Zeynep Akata, Gaurav Sharma, Quynh Nguyen, Matthias Hein, Bernt Schiele
2016 J jnl
Latent Embeddings for Zero-shot Classification.
CoRR
Yongqin Xian, Zeynep Akata, Gaurav Sharma, Quynh Nguyen, Matthias Hein, Bernt Schiele
2015 J jnl
An Efficient Multilinear Optimization Framework for Hypergraph Matching.
CoRR
Quynh Nguyen, Francesco Tudisco, Antoine Gautier, Matthias Hein