
On Connectivity of Solutions in Deep Learning: The Role of Overparameterization and Feature Quality
It has been empirically observed that, in deep neural networks, the solu...
read it

On the Proof of Global Convergence of Gradient Descent for Deep ReLU Networks with Linear Widths
This paper studies the global convergence of gradient descent for deep R...
read it

A Note on Connectivity of Sublevel Sets in Deep Learning
It is shown that for deep neural networks, a single wide layer of width ...
read it

Tight Bounds on the Smallest Eigenvalue of the Neural Tangent Kernel for Deep ReLU Networks
A recent line of work has analyzed the theoretical properties of deep ne...
read it

Global Convergence of Deep Networks with One Wide Layer Followed by Pyramidal Topology
A recent line of research has provided convergence guarantees for gradie...
read it

Jupiter: A Networked Computing Architecture
In the era of Internet of Things, there is an increasing demand for netw...
read it

On Connected Sublevel Sets in Deep Learning
We study sublevel sets of the loss function in training deep neural netw...
read it

On the loss landscape of a class of deep neural networks with no bad local valleys
We identify a class of overparameterized deep neural networks with stan...
read it

Neural Networks Should Be Wide Enough to Learn Disconnected Decision Regions
In the recent literature the important role of depth in deep learning ha...
read it

The loss surface and expressivity of deep convolutional neural networks
We analyze the expressiveness and loss surface of practical deep convolu...
read it

The loss surface of deep and wide neural networks
While the optimization problem behind deep neural networks is highly non...
read it

Globally Optimal Training of Generalized Polynomial Neural Networks with Nonlinear Spectral Methods
The optimization problem behind neural networks is highly nonconvex. Tr...
read it

Latent Embeddings for Zeroshot Classification
We present a novel latent embedding model for learning a compatibility f...
read it

An Efficient Multilinear Optimization Framework for Hypergraph Matching
Hypergraph matching has recently become a popular approach for solving c...
read it

A Flexible Tensor Block Coordinate Ascent Scheme for Hypergraph Matching
The estimation of correspondences between two images resp. point sets is...
read it
Quynh Nguyen
is this you? claim profile